Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,73 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+license.pdf filter=lfs diff=lfs merge=lfs -text
+vocoder/female/assamese_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/bengali_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/bodo_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/dogri_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/gujarati_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/hindi_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/kannada_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/konkani_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/maithili_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/malayalam_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/manipuri_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/nepali_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/punjabi_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/rajasthani_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/sanskrit_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/sindhi_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/tamil_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/female/telugu_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/assamese_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/bengali_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/bodo_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/dogri_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/gujarati_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/hindi_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/kannada_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/konkani_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/maithili_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/malayalam_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/manipuri_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/nepali_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/punjabi_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/rajasthani_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/sanskrit_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/sindhi_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/tamil_latest/generator filter=lfs diff=lfs merge=lfs -text
+vocoder/male/telugu_latest/generator filter=lfs diff=lfs merge=lfs -text
+ssn_parser_new/scripts/tamil_trans_py filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,395 @@
+Attribution 4.0 International
+
+=======================================================================
+
+Creative Commons Corporation ("Creative Commons") is not a law firm and
+does not provide legal services or legal advice. Distribution of
+Creative Commons public licenses does not create a lawyer-client or
+other relationship. Creative Commons makes its licenses and related
+information available on an "as-is" basis. Creative Commons gives no
+warranties regarding its licenses, any material licensed under their
+terms and conditions, or any related information. Creative Commons
+disclaims all liability for damages resulting from their use to the
+fullest extent possible.
+
+Using Creative Commons Public Licenses
+
+Creative Commons public licenses provide a standard set of terms and
+conditions that creators and other rights holders may use to share
+original works of authorship and other material subject to copyright
+and certain other rights specified in the public license below. The
+following considerations are for informational purposes only, are not
+exhaustive, and do not form part of our licenses.
+
+     Considerations for licensors: Our public licenses are
+     intended for use by those authorized to give the public
+     permission to use material in ways otherwise restricted by
+     copyright and certain other rights. Our licenses are
+     irrevocable. Licensors should read and understand the terms
+     and conditions of the license they choose before applying it.
+     Licensors should also secure all rights necessary before
+     applying our licenses so that the public can reuse the
+     material as expected. Licensors should clearly mark any
+     material not subject to the license. This includes other CC-
+     licensed material, or material used under an exception or
+     limitation to copyright. More considerations for licensors:
+	wiki.creativecommons.org/Considerations_for_licensors
+
+     Considerations for the public: By using one of our public
+     licenses, a licensor grants the public permission to use the
+     licensed material under specified terms and conditions. If
+     the licensor's permission is not necessary for any reason--for
+     example, because of any applicable exception or limitation to
+     copyright--then that use is not regulated by the license. Our
+     licenses grant only permissions under copyright and certain
+     other rights that a licensor has authority to grant. Use of
+     the licensed material may still be restricted for other
+     reasons, including because others have copyright or other
+     rights in the material. A licensor may make special requests,
+     such as asking that all changes be marked or described.
+     Although not required by our licenses, you are encouraged to
+     respect those requests where reasonable. More_considerations
+     for the public:
+	wiki.creativecommons.org/Considerations_for_licensees
+
+=======================================================================
+
+Creative Commons Attribution 4.0 International Public License
+
+By exercising the Licensed Rights (defined below), You accept and agree
+to be bound by the terms and conditions of this Creative Commons
+Attribution 4.0 International Public License ("Public License"). To the
+extent this Public License may be interpreted as a contract, You are
+granted the Licensed Rights in consideration of Your acceptance of
+these terms and conditions, and the Licensor grants You such rights in
+consideration of benefits the Licensor receives from making the
+Licensed Material available under these terms and conditions.
+
+
+Section 1 -- Definitions.
+
+  a. Adapted Material means material subject to Copyright and Similar
+     Rights that is derived from or based upon the Licensed Material
+     and in which the Licensed Material is translated, altered,
+     arranged, transformed, or otherwise modified in a manner requiring
+     permission under the Copyright and Similar Rights held by the
+     Licensor. For purposes of this Public License, where the Licensed
+     Material is a musical work, performance, or sound recording,
+     Adapted Material is always produced where the Licensed Material is
+     synched in timed relation with a moving image.
+
+  b. Adapter's License means the license You apply to Your Copyright
+     and Similar Rights in Your contributions to Adapted Material in
+     accordance with the terms and conditions of this Public License.
+
+  c. Copyright and Similar Rights means copyright and/or similar rights
+     closely related to copyright including, without limitation,
+     performance, broadcast, sound recording, and Sui Generis Database
+     Rights, without regard to how the rights are labeled or
+     categorized. For purposes of this Public License, the rights
+     specified in Section 2(b)(1)-(2) are not Copyright and Similar
+     Rights.
+
+  d. Effective Technological Measures means those measures that, in the
+     absence of proper authority, may not be circumvented under laws
+     fulfilling obligations under Article 11 of the WIPO Copyright
+     Treaty adopted on December 20, 1996, and/or similar international
+     agreements.
+
+  e. Exceptions and Limitations means fair use, fair dealing, and/or
+     any other exception or limitation to Copyright and Similar Rights
+     that applies to Your use of the Licensed Material.
+
+  f. Licensed Material means the artistic or literary work, database,
+     or other material to which the Licensor applied this Public
+     License.
+
+  g. Licensed Rights means the rights granted to You subject to the
+     terms and conditions of this Public License, which are limited to
+     all Copyright and Similar Rights that apply to Your use of the
+     Licensed Material and that the Licensor has authority to license.
+
+  h. Licensor means the individual(s) or entity(ies) granting rights
+     under this Public License.
+
+  i. Share means to provide material to the public by any means or
+     process that requires permission under the Licensed Rights, such
+     as reproduction, public display, public performance, distribution,
+     dissemination, communication, or importation, and to make material
+     available to the public including in ways that members of the
+     public may access the material from a place and at a time
+     individually chosen by them.
+
+  j. Sui Generis Database Rights means rights other than copyright
+     resulting from Directive 96/9/EC of the European Parliament and of
+     the Council of 11 March 1996 on the legal protection of databases,
+     as amended and/or succeeded, as well as other essentially
+     equivalent rights anywhere in the world.
+
+  k. You means the individual or entity exercising the Licensed Rights
+     under this Public License. Your has a corresponding meaning.
+
+
+Section 2 -- Scope.
+
+  a. License grant.
+
+       1. Subject to the terms and conditions of this Public License,
+          the Licensor hereby grants You a worldwide, royalty-free,
+          non-sublicensable, non-exclusive, irrevocable license to
+          exercise the Licensed Rights in the Licensed Material to:
+
+            a. reproduce and Share the Licensed Material, in whole or
+               in part; and
+
+            b. produce, reproduce, and Share Adapted Material.
+
+       2. Exceptions and Limitations. For the avoidance of doubt, where
+          Exceptions and Limitations apply to Your use, this Public
+          License does not apply, and You do not need to comply with
+          its terms and conditions.
+
+       3. Term. The term of this Public License is specified in Section
+          6(a).
+
+       4. Media and formats; technical modifications allowed. The
+          Licensor authorizes You to exercise the Licensed Rights in
+          all media and formats whether now known or hereafter created,
+          and to make technical modifications necessary to do so. The
+          Licensor waives and/or agrees not to assert any right or
+          authority to forbid You from making technical modifications
+          necessary to exercise the Licensed Rights, including
+          technical modifications necessary to circumvent Effective
+          Technological Measures. For purposes of this Public License,
+          simply making modifications authorized by this Section 2(a)
+          (4) never produces Adapted Material.
+
+       5. Downstream recipients.
+
+            a. Offer from the Licensor -- Licensed Material. Every
+               recipient of the Licensed Material automatically
+               receives an offer from the Licensor to exercise the
+               Licensed Rights under the terms and conditions of this
+               Public License.
+
+            b. No downstream restrictions. You may not offer or impose
+               any additional or different terms or conditions on, or
+               apply any Effective Technological Measures to, the
+               Licensed Material if doing so restricts exercise of the
+               Licensed Rights by any recipient of the Licensed
+               Material.
+
+       6. No endorsement. Nothing in this Public License constitutes or
+          may be construed as permission to assert or imply that You
+          are, or that Your use of the Licensed Material is, connected
+          with, or sponsored, endorsed, or granted official status by,
+          the Licensor or others designated to receive attribution as
+          provided in Section 3(a)(1)(A)(i).
+
+  b. Other rights.
+
+       1. Moral rights, such as the right of integrity, are not
+          licensed under this Public License, nor are publicity,
+          privacy, and/or other similar personality rights; however, to
+          the extent possible, the Licensor waives and/or agrees not to
+          assert any such rights held by the Licensor to the limited
+          extent necessary to allow You to exercise the Licensed
+          Rights, but not otherwise.
+
+       2. Patent and trademark rights are not licensed under this
+          Public License.
+
+       3. To the extent possible, the Licensor waives any right to
+          collect royalties from You for the exercise of the Licensed
+          Rights, whether directly or through a collecting society
+          under any voluntary or waivable statutory or compulsory
+          licensing scheme. In all other cases the Licensor expressly
+          reserves any right to collect such royalties.
+
+
+Section 3 -- License Conditions.
+
+Your exercise of the Licensed Rights is expressly made subject to the
+following conditions.
+
+  a. Attribution.
+
+       1. If You Share the Licensed Material (including in modified
+          form), You must:
+
+            a. retain the following if it is supplied by the Licensor
+               with the Licensed Material:
+
+                 i. identification of the creator(s) of the Licensed
+                    Material and any others designated to receive
+                    attribution, in any reasonable manner requested by
+                    the Licensor (including by pseudonym if
+                    designated);
+
+                ii. a copyright notice;
+
+               iii. a notice that refers to this Public License;
+
+                iv. a notice that refers to the disclaimer of
+                    warranties;
+
+                 v. a URI or hyperlink to the Licensed Material to the
+                    extent reasonably practicable;
+
+            b. indicate if You modified the Licensed Material and
+               retain an indication of any previous modifications; and
+
+            c. indicate the Licensed Material is licensed under this
+               Public License, and include the text of, or the URI or
+               hyperlink to, this Public License.
+
+       2. You may satisfy the conditions in Section 3(a)(1) in any
+          reasonable manner based on the medium, means, and context in
+          which You Share the Licensed Material. For example, it may be
+          reasonable to satisfy the conditions by providing a URI or
+          hyperlink to a resource that includes the required
+          information.
+
+       3. If requested by the Licensor, You must remove any of the
+          information required by Section 3(a)(1)(A) to the extent
+          reasonably practicable.
+
+       4. If You Share Adapted Material You produce, the Adapter's
+          License You apply must not prevent recipients of the Adapted
+          Material from complying with this Public License.
+
+
+Section 4 -- Sui Generis Database Rights.
+
+Where the Licensed Rights include Sui Generis Database Rights that
+apply to Your use of the Licensed Material:
+
+  a. for the avoidance of doubt, Section 2(a)(1) grants You the right
+     to extract, reuse, reproduce, and Share all or a substantial
+     portion of the contents of the database;
+
+  b. if You include all or a substantial portion of the database
+     contents in a database in which You have Sui Generis Database
+     Rights, then the database in which You have Sui Generis Database
+     Rights (but not its individual contents) is Adapted Material; and
+
+  c. You must comply with the conditions in Section 3(a) if You Share
+     all or a substantial portion of the contents of the database.
+
+For the avoidance of doubt, this Section 4 supplements and does not
+replace Your obligations under this Public License where the Licensed
+Rights include other Copyright and Similar Rights.
+
+
+Section 5 -- Disclaimer of Warranties and Limitation of Liability.
+
+  a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
+     EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
+     AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
+     ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
+     IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
+     WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
+     PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
+     ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
+     KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
+     ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
+
+  b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
+     TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
+     NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
+     INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
+     COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
+     USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
+     ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
+     DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
+     IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
+
+  c. The disclaimer of warranties and limitation of liability provided
+     above shall be interpreted in a manner that, to the extent
+     possible, most closely approximates an absolute disclaimer and
+     waiver of all liability.
+
+
+Section 6 -- Term and Termination.
+
+  a. This Public License applies for the term of the Copyright and
+     Similar Rights licensed here. However, if You fail to comply with
+     this Public License, then Your rights under this Public License
+     terminate automatically.
+
+  b. Where Your right to use the Licensed Material has terminated under
+     Section 6(a), it reinstates:
+
+       1. automatically as of the date the violation is cured, provided
+          it is cured within 30 days of Your discovery of the
+          violation; or
+
+       2. upon express reinstatement by the Licensor.
+
+     For the avoidance of doubt, this Section 6(b) does not affect any
+     right the Licensor may have to seek remedies for Your violations
+     of this Public License.
+
+  c. For the avoidance of doubt, the Licensor may also offer the
+     Licensed Material under separate terms or conditions or stop
+     distributing the Licensed Material at any time; however, doing so
+     will not terminate this Public License.
+
+  d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
+     License.
+
+
+Section 7 -- Other Terms and Conditions.
+
+  a. The Licensor shall not be bound by any additional or different
+     terms or conditions communicated by You unless expressly agreed.
+
+  b. Any arrangements, understandings, or agreements regarding the
+     Licensed Material not stated herein are separate from and
+     independent of the terms and conditions of this Public License.
+
+
+Section 8 -- Interpretation.
+
+  a. For the avoidance of doubt, this Public License does not, and
+     shall not be interpreted to, reduce, limit, restrict, or impose
+     conditions on any use of the Licensed Material that could lawfully
+     be made without permission under this Public License.
+
+  b. To the extent possible, if any provision of this Public License is
+     deemed unenforceable, it shall be automatically reformed to the
+     minimum extent necessary to make it enforceable. If the provision
+     cannot be reformed, it shall be severed from this Public License
+     without affecting the enforceability of the remaining terms and
+     conditions.
+
+  c. No term or condition of this Public License will be waived and no
+     failure to comply consented to unless expressly agreed to by the
+     Licensor.
+
+  d. Nothing in this Public License constitutes or may be interpreted
+     as a limitation upon, or waiver of, any privileges and immunities
+     that apply to the Licensor or You, including from the legal
+     processes of any jurisdiction or authority.
+
+
+=======================================================================
+
+Creative Commons is not a party to its public
+licenses. Notwithstanding, Creative Commons may elect to apply one of
+its public licenses to material it publishes and in those instances
+will be considered the “Licensor.” The text of the Creative Commons
+public licenses is dedicated to the public domain under the CC0 Public
+Domain Dedication. Except for the limited purpose of indicating that
+material is shared under a Creative Commons public license or as
+otherwise permitted by the Creative Commons policies published at
+creativecommons.org/policies, Creative Commons does not authorize the
+use of the trademark "Creative Commons" or any other trademark or logo
+of Creative Commons without its prior written consent including,
+without limitation, in connection with any unauthorized modifications
+to any of its public licenses or any other arrangements,
+understandings, or agreements concerning use of licensed material. For
+the avoidance of doubt, this paragraph does not form part of the
+public licenses.
+
+Creative Commons may be contacted at creativecommons.org.

NumberToText.py

@@ -0,0 +1,96 @@
+import os
+import csv
+
+class NumberDictionary:
+    def __init__(self):
+        directoryPath = "numToText"
+        # print(directoryPath)
+        languages = self.get_filenames_in_folder(directoryPath)
+        # print(languages, directoryPath)
+        self.lang_num_dictionary = self.load_language_dictionary(directoryPath, languages)
+        # print(self.lang_num_dictionary)
+
+        
+
+    def get_filenames_in_folder(self,folder_path):
+        file_list = []
+        
+        # Loop through the files in the directory
+        for filename in os.listdir(folder_path):
+            # Check if it's a file (not a subdirectory)
+            if os.path.isfile(os.path.join(folder_path, filename)):
+                file_list.append(filename[:-4])
+        
+        return file_list
+
+
+    def load_language_dictionary(self, directory_path, file_names):
+        lang_num_dictionary = {}
+
+        for file_name in file_names:
+            language = os.path.splitext(file_name)[0]
+            file_path = os.path.join(directory_path, f"{file_name}.csv")
+            if not os.path.exists(file_path):
+                # print(f"File '{file_path}' not found. Skipping...")
+                continue
+
+            with open(file_path, 'r', encoding='utf-8') as file:
+                reader = csv.reader(file)
+                language_map = {row[0].strip(): row[1].strip() for row in reader}
+
+            lang_num_dictionary[language] = language_map
+
+        return lang_num_dictionary
+
+    def num2text(self, input_str, language):
+        if language not in self.lang_num_dictionary:
+            return "Language not supported."
+
+        integer_part, *decimal_part = input_str.split('.')
+        try:
+            int_part = int(integer_part)
+        except ValueError:
+            return "Invalid input. Please provide a valid number."
+
+        if int_part < 0 or int_part > 999999999999999:
+            return "Number out of range (0-999999999999999)"
+
+        lang_map = self.lang_num_dictionary[language]
+        integer_text = self.convert_to_indian_number(int_part, lang_map)
+
+        if decimal_part:
+            decimal_text = lang_map.get('.', '') + ' '
+            for digit in decimal_part[0]:
+                decimal_text += lang_map.get(digit, '') + ' '
+            return (integer_text + ' ' + decimal_text).strip()
+        else:
+            return integer_text.strip()
+
+    def convert_to_indian_number(self, n, lang_map):
+        numeric_keys = [key for key in lang_map.keys() if key.isdigit()]  # Filter numeric keys
+        if n <= 20 or (n <= 100 and str(n) in lang_map):
+            return lang_map.get(str(n), '')
+        elif n < 1000:
+            result = f"{lang_map.get(str(n // 100), '')} {lang_map.get('100', '')}"
+            if n % 100 != 0:
+                result += f" {self.convert_to_indian_number(n % 100, lang_map)}"
+            return result.strip()
+        else:
+            base, term = 0, ''
+            for key in sorted(numeric_keys, key=int, reverse=True):  # Sort only numeric keys
+                if n >= int(key):
+                    base = int(key)
+                    term = lang_map[key]
+                    break
+
+            if n % base == 0:
+                return f"{self.convert_to_indian_number(n // base, lang_map)} {term}"
+            else:
+                return f"{self.convert_to_indian_number(n // base, lang_map)} {term} {self.convert_to_indian_number(n % base, lang_map)}"
+
+
+
+
+# number_dict = NumberDictionary()
+# result = number_dict.num2text("2000048.145", "gujarati")
+# print(result)

README.md

@@ -1,3 +1,118 @@
 ---
 license: cc-by-4.0
+language:
+- hi
+- as
+- bn
+- bo
+- en
+- gu
+- kn
+- ml
+- mr
+- or
+- pa
+- ta
+- te
+- ur
+tags:
+- tts
+- indictts
+- fs2
+- mfa
+- HS
+- hybrid_segmentation
+- fastspeech2
 ---
+# Latest Fastspeech2 Models using FLAT Start
+
+This repository contains new and high quality Fastspeech2 Models for Indian languages implemented using the Flat Start for speech synthesis. The models are capable of generating mel-spectrograms from text inputs and can be used to synthesize speech. 
+
+The Repo is large in size. New Models are in "language"_latest folder.
+
+Supported languages: Assamese, Bengali, Bodo, Dogri, Gujarati, Hindi, Kannada, Konkani(Maharashtrian), Maithili, Malayalam, Manipuri, Nepali, Punjabi, Rajasthani, Sanskrit, Tamil, Telugu.
+
+NOTE - I do not own any right to the repository, all the rights goes to original owner. This repository is meant to help easy installation of the speech models.
+
+## Model Files
+
+The model for each language includes the following files:
+
+- `config.yaml`: Configuration file for the Fastspeech2 Model.
+- `energy_stats.npz`: Energy statistics for normalization during synthesis.
+- `feats_stats.npz`: Features statistics for normalization during synthesis.
+- `feats_type`: Features type information.
+- `pitch_stats.npz`: Pitch statistics for normalization during synthesis.
+- `model.pth`: Pre-trained Fastspeech2 model weights.
+
+## Installation
+
+1. Install [Miniconda](https://docs.conda.io/projects/miniconda/en/latest/) first. Create a conda environment using the provided `environment.yml` file:
+
+```shell
+conda env create -f environment.yml
+```
+
+2.Activate the conda environment (check inside environment.yaml file):
+```shell
+conda activate tts-hs-hifigan
+```
+
+3.  Install PyTorch separately (you can install the specific version based on your requirements):
+```shell
+conda install pytorch cudatoolkit
+pip install torchaudio
+```
+## Vocoder
+For generating WAV files from mel-spectrograms, you can use a vocoder of your choice. One popular option is the [HIFIGAN](https://github.com/jik876/hifi-gan) vocoder (Clone this repo and put it in the current working directory). Please refer to the documentation of the vocoder you choose for installation and usage instructions. 
+
+(**We have used the HIFIGAN V1 vocoder and have provided Vocoder for few languages in the Vocoder folder. If needed, make sure to adjust the path in the inference file.**)
+
+## Usage
+
+The directory paths are Relative. ( But if needed, Make changes to **text_preprocess_for_inference.py** and **inference.py** file, Update folder/file paths wherever required.)
+
+**Please give language/gender in small cases and sample text between quotes. Adjust output speed using the alpha parameter (higher for slow voiced output and vice versa). Output argument is optional; the provide name will be used for the output file.** 
+
+Use the inference file to synthesize speech from text inputs:
+```shell
+python inference.py --sample_text "Your input text here" --language <language>_latest --gender <gender> --alpha <alpha> --output_file <file_name.wav OR path/to/file_name.wav>
+```
+
+**Example:**
+
+```
+python inference.py --sample_text "श्रीलंका और पाकिस्तान में खेला जा रहा एशिया कप अब तक का सबसे विवादित टूर्नामेंट होता जा रहा है।" --language hindi_latest --gender male --alpha 1 --output_file male_hindi_output.wav
+```
+The file will be stored as `male_hindi_output.wav` and will be inside current working directory. If **--output_file** argument is not given it will be stored as `<language>_<gender>_output.wav` in the current working directory.
+
+**Use "language"_latest in --language to use latest models.**
+
+
+### Citation
+If you use this Fastspeech2 Model in your research or work, please consider citing:
+
+“
+COPYRIGHT
+2025, Speech Technology Consortium,
+
+Bhashini, MeiTY and by Hema A Murthy & S Umesh,
+
+
+DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
+and
+ELECTRICAL ENGINEERING,
+IIT MADRAS. ALL RIGHTS RESERVED "
+
+
+
+Shield: [![CC BY 4.0][cc-by-shield]][cc-by]
+
+This work is licensed under a
+[Creative Commons Attribution 4.0 International License][cc-by].
+
+[![CC BY 4.0][cc-by-image]][cc-by]
+
+[cc-by]: http://creativecommons.org/licenses/by/4.0/
+[cc-by-image]: https://i.creativecommons.org/l/by/4.0/88x31.png
+[cc-by-shield]: https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg

api.py

@@ -0,0 +1,63 @@
+# TTS IITM SPEECH LAB
+import requests
+import json
+import base64
+  
+text = "सुप्रभात, आप कैसे हैं?" # hindi
+# text = "സുപ്രഭാതം, സുഖമാ?" # malayalam
+# text = "সুপ্ৰভাত, তুমি কেনে?" # manipuri
+# text = "सुप्रभात, तुम्ही कसे आहात?" # marathi
+# text = "ಶುಭೋದಯ, ನೀವು ಹೇಗಿದ್ದೀರಿ?" # kannada
+# text = "बसु म्विथ्बो, बरि दिबाबो?" # bodo male not working <---
+# text = "Good morning, how are you?" # english
+# text = "সুপ্ৰভাত, আপুনি কেমন আছে?" # assamese
+# text = "காலை வணக்கம், நீங்கள் எப்படி இருக்கின்றீர்கள்?" # tamil
+# text = "ସୁପ୍ରଭାତ, ଆପଣ କେମିତି ଅଛନ୍ତି?" # odia male not working <---
+# text = "सुप्रभात, आप कैसे छो?" # rajasthani
+# text = "శుభోదయం, మీరు ఎలా ఉన్నారు?" # telugu
+# text = "সুপ্রভাত, আপনি কেমন আছেন?" # bengali male not working <---
+# text = "સુપ્રભાત, તમે કેમ છો?" # gujarati
+
+lang = 'hindi'
+gender = 'female'
+
+url = "http://localhost:4005/tts"
+# url = 'http://projects.respark.iitm.ac.in:8009/tts' # proxy
+
+payload = json.dumps({
+"input": text,
+"gender": gender,
+"lang": lang,
+"alpha": 1,
+"segmentwise":"True"
+})
+headers = {'Content-Type': 'application/json'}
+response = requests.request("POST", url, headers=headers, data=payload).json()
+
+audio = response['audio']
+file_name = "tts.mp3"
+wav_file = open(file_name,'wb')
+decode_string = base64.b64decode(audio)
+wav_file.write(decode_string)
+wav_file.close()
+
+'''
+Supported languages
+
+Assamese
+Bengali
+Bodo
+English
+Gujarati
+Hindi
+Kannada
+Malayalam
+Manipuri
+Marathi
+Odia
+Punjabi
+Rajasthani
+Tamil
+Telugu
+Urdu
+'''

app.py

@@ -0,0 +1,179 @@
+from flask import Flask, render_template, request, send_file, jsonify
+import requests
+import json
+import ssl
+import logging
+import sys
+import os
+import base64
+import io
+#replace the path with your hifigan path to import Generator from models.py 
+sys.path.append("hifigan")
+# import argparse
+import torch
+from espnet2.bin.tts_inference import Text2Speech
+from models import Generator
+from scipy.io.wavfile import write
+from meldataset import MAX_WAV_VALUE
+from env import AttrDict
+import json
+import yaml
+from text_preprocess_for_inference import TTSDurAlignPreprocessor
+# import time
+
+logging.basicConfig(filename='access.log', level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+SAMPLING_RATE = 22050
+if torch.cuda.is_available():
+    device = "cuda"
+else:
+    device = "cpu"
+
+preprocessor = TTSDurAlignPreprocessor()
+
+app = Flask(__name__)
+# app.config['SECRET_KEY'] = 'key'
+# socketio = SocketIO(app)
+
+# @socketio.on('new_user')
+# def handle_new_user(data):
+#     client_id = data['id']
+#     # print('\n'+f"New user connected with ID: {client_id}")
+#     logging.info('\n'+f"New user connected with ID: {client_id}")
+
+def load_hifigan_vocoder(language, gender, device):
+    # Load HiFi-GAN vocoder configuration file and generator model for the specified language and gender
+    vocoder_config = f"vocoder/{gender}/aryan/hifigan/config.json"
+    vocoder_generator = f"vocoder/{gender}/aryan/hifigan/generator"
+    # Read the contents of the vocoder configuration file
+    with open(vocoder_config, 'r') as f:
+        data = f.read()
+    json_config = json.loads(data)
+    h = AttrDict(json_config)
+    torch.manual_seed(h.seed)
+    # Move the generator model to the specified device (CPU or GPU)
+    device = torch.device(device)
+    generator = Generator(h).to(device)
+    state_dict_g = torch.load(vocoder_generator, device)
+    generator.load_state_dict(state_dict_g['generator'])
+    generator.eval()
+    generator.remove_weight_norm()
+
+    # Return the loaded and prepared HiFi-GAN generator model
+    return generator
+
+def load_fastspeech2_model(language, gender, device):
+    
+    #updating the config.yaml fiel based on language and gender
+    with open(f"{language}/{gender}/model/config.yaml", "r") as file:      
+     config = yaml.safe_load(file)
+    
+    current_working_directory = os.getcwd()
+    feat="model/feats_stats.npz"
+    pitch="model/pitch_stats.npz"
+    energy="model/energy_stats.npz"
+    
+    feat_path=os.path.join(current_working_directory,language,gender,feat)
+    pitch_path=os.path.join(current_working_directory,language,gender,pitch)
+    energy_path=os.path.join(current_working_directory,language,gender,energy)
+
+    
+    config["normalize_conf"]["stats_file"]  = feat_path
+    config["pitch_normalize_conf"]["stats_file"]  = pitch_path
+    config["energy_normalize_conf"]["stats_file"]  = energy_path
+        
+    with open(f"{language}/{gender}/model/config.yaml", "w") as file:
+        yaml.dump(config, file)
+    
+    tts_model = f"{language}/{gender}/model/model.pth"
+    tts_config = f"{language}/{gender}/model/config.yaml"
+    
+    
+    return Text2Speech(train_config=tts_config, model_file=tts_model, device=device)
+
+def text_synthesis(language, gender, sample_text, vocoder, MAX_WAV_VALUE, device, alpha=1):
+    # Perform Text-to-Speech synthesis
+    with torch.no_grad():
+        # Load the FastSpeech2 model for the specified language and gender
+        
+        model = load_fastspeech2_model(language, gender, device)
+       
+        # Generate mel-spectrograms from the input text using the FastSpeech2 model
+        out = model(sample_text, decode_conf={"alpha": alpha})
+        print("TTS Done")  
+        x = out["feat_gen_denorm"].T.unsqueeze(0) * 2.3262
+        x = x.to(device)
+        
+        # Use the HiFi-GAN vocoder to convert mel-spectrograms to raw audio waveforms
+        y_g_hat = vocoder(x)
+        audio = y_g_hat.squeeze()
+        audio = audio * MAX_WAV_VALUE
+        audio = audio.cpu().numpy().astype('int16')
+        
+        # Return the synthesized audio
+        return audio
+
+def setup_app():
+    genders = ['male','female']
+    # to make dummy calls in all languages available
+    languages = {'hindi': "नमस्ते",'malayalam': "ഹലോ",'manipuri': "হ্যালো",'marathi': "हॅलो",'kannada': "ಹಲೋ",'bodo': "हॅलो",'english': "Hello",'assamese': "হ্যালো",'tamil': "ஹலோ",'odia': "ହେଲୋ",'rajasthani': "हॅलो",'telugu': "హలో",'bengali': "হ্যালো",'gujarati': "હલો"}
+    
+    vocoders = {}
+    for gender in genders:
+        vocoders[gender]={}
+        for language,text in languages.items():
+            # Load the HiFi-GAN vocoder with dynamic language and gender
+            vocoder = load_hifigan_vocoder(language, gender, device)
+            vocoders[gender][language] = vocoder
+            # dummy calls
+            print(f"making dummy calls for {language} - {gender}")
+            try:
+                out = text_synthesis(language, gender, text, vocoder, MAX_WAV_VALUE, device)
+            except:
+                message = f"cannot make dummy call for {gender} - {language} <==================="
+                print(message.upper())
+                
+    print("Server Started...")
+    return vocoders
+vocoders = setup_app()
+
+@app.route('/', methods=['GET'])
+def main():
+    return "IITM_TTS_V2"
+
+@app.route('/tts', methods=['GET', 'POST'], strict_slashes=False)
+def tts():
+    try:
+        json_data = request.get_json()
+        text = json_data["input"]
+        if not isinstance(text,str):
+            input_type = type(text)
+            ret = jsonify(status='failure', reason=f"Unsupported input type {input_type}. Input text should be in string format.")
+        gender = json_data["gender"]
+        language = json_data["lang"].lower()
+        alpha = json_data["alpha"]
+        # Preprocess the sample text
+        preprocessed_text, phrases = preprocessor.preprocess(text, language, gender)
+        preprocessed_text = " ".join(preprocessed_text)
+        vocoder = vocoders[gender][language]
+        out = text_synthesis(language, gender, preprocessed_text, vocoder, MAX_WAV_VALUE, device, alpha=alpha)
+        
+        # output_file = f"{language}_{gender}_output.wav"
+        # write(output_file, SAMPLING_RATE, out)
+        # audio_wav_bytes = base64.b64encode(open(output_file, "rb").read())
+
+        # avoid saving file on disk
+        output_stream = io.BytesIO()
+        write(output_stream, SAMPLING_RATE, out)
+        audio_wav_bytes = base64.b64encode(output_stream.getvalue())
+
+        ret = jsonify(status="success",audio=audio_wav_bytes.decode('utf-8'))
+
+    except Exception as err:
+        ret = jsonify(status="failure", reason=str(err))
+    return ret
+
+if __name__ == '__main__':
+    # ssl_context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH)
+    # ssl_context.load_cert_chain('./ssl2023/iitm2022.crt','./ssl2023/iitm2022.key')
+    app.run(host='0.0.0.0', port=4005, debug=True)

assamese_latest/female/model/config.yaml

@@ -0,0 +1,319 @@
+config: conf/tuning/train_fastspeech2.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/tts_train_fastspeech2_raw_char_None
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 2
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 36807
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: false
+sharded_ddp: false
+use_deepspeed: false
+deepspeed_config: null
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 1000
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+-   - train
+    - loss
+    - min
+keep_nbest_models: 5
+nbest_averaging_interval: 0
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 8
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+use_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 800
+batch_size: 20
+valid_batch_size: null
+batch_bins: 3000000
+valid_batch_bins: null
+train_shape_file:
+- exp/tts_stats_raw_char_None/train/text_shape.char
+- exp/tts_stats_raw_char_None/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_char_None/valid/text_shape.char
+- exp/tts_stats_raw_char_None/valid/speech_shape
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+- 819200
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: null
+chunk_max_abs_length: null
+chunk_discard_short_samples: true
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_no_dev/text
+    - text
+    - text
+-   - duration_info/tr_no_dev/durations
+    - durations
+    - text_int
+-   - dump/raw/tr_no_dev/wav.scp
+    - speech
+    - sound
+-   - exp/tts_stats_raw_char_None/train/collect_feats/pitch.scp
+    - pitch
+    - npy
+-   - exp/tts_stats_raw_char_None/train/collect_feats/energy.scp
+    - energy
+    - npy
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/text
+    - text
+    - text
+-   - duration_info/dev/durations
+    - durations
+    - text_int
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - exp/tts_stats_raw_char_None/valid/collect_feats/pitch.scp
+    - pitch
+    - npy
+-   - exp/tts_stats_raw_char_None/valid/collect_feats/energy.scp
+    - energy
+    - npy
+multi_task_dataset: false
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: false
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 1.0
+scheduler: noamlr
+scheduler_conf:
+    model_size: 384
+    warmup_steps: 4000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- $
+- ','
+- .
+- M
+- q
+- H
+- k
+- ख
+- g
+- घ
+- ङ
+- c
+- C
+- j
+- J
+- ञ
+- ट
+- ठ
+- ड
+- ढ
+- ण
+- t
+- थ
+- d
+- ध
+- n
+- ऩ
+- p
+- P
+- b
+- B
+- m
+- y
+- r
+- ऱ
+- l
+- ള
+- Z
+- w
+- श
+- ष
+- s
+- h
+- Y
+- ऽ
+- क
+- K
+- G
+- z
+- D
+- T
+- f
+- ॠ
+- ൺ
+- N
+- ർ
+- ൽ
+- ൾ
+- a
+- A
+- i
+- I
+- u
+- U
+- R
+- ऍ
+- e
+- E
+- ऐ
+- ऑ
+- o
+- O
+- औ
+- உ
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+feats_extract: fbank
+feats_extract_conf:
+    n_fft: 8192
+    hop_length: 1024
+    win_length: 4096
+    fs: 48000
+    fmin: 0
+    fmax: 24000
+    n_mels: 160
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/tts_stats_raw_char_None/train/feats_stats.npz
+tts: fastspeech2
+tts_conf:
+    adim: 384
+    aheads: 2
+    elayers: 4
+    eunits: 1536
+    dlayers: 4
+    dunits: 1536
+    positionwise_layer_type: conv1d
+    positionwise_conv_kernel_size: 3
+    duration_predictor_layers: 2
+    duration_predictor_chans: 256
+    duration_predictor_kernel_size: 3
+    postnet_layers: 5
+    postnet_filts: 5
+    postnet_chans: 256
+    use_masking: true
+    use_scaled_pos_enc: true
+    encoder_normalize_before: true
+    decoder_normalize_before: true
+    reduction_factor: 1
+    init_type: xavier_uniform
+    init_enc_alpha: 1.0
+    init_dec_alpha: 1.0
+    transformer_enc_dropout_rate: 0.2
+    transformer_enc_positional_dropout_rate: 0.2
+    transformer_enc_attn_dropout_rate: 0.2
+    transformer_dec_dropout_rate: 0.2
+    transformer_dec_positional_dropout_rate: 0.2
+    transformer_dec_attn_dropout_rate: 0.2
+    pitch_predictor_layers: 5
+    pitch_predictor_chans: 256
+    pitch_predictor_kernel_size: 5
+    pitch_predictor_dropout: 0.5
+    pitch_embed_kernel_size: 1
+    pitch_embed_dropout: 0.0
+    stop_gradient_from_pitch_predictor: true
+    energy_predictor_layers: 2
+    energy_predictor_chans: 256
+    energy_predictor_kernel_size: 3
+    energy_predictor_dropout: 0.5
+    energy_embed_kernel_size: 1
+    energy_embed_dropout: 0.0
+    stop_gradient_from_energy_predictor: false
+pitch_extract: dio
+pitch_extract_conf:
+    fs: 48000
+    n_fft: 8192
+    hop_length: 1024
+    f0max: 400
+    f0min: 80
+    reduction_factor: 1
+pitch_normalize: global_mvn
+pitch_normalize_conf:
+    stats_file: exp/tts_stats_raw_char_None/train/pitch_stats.npz
+energy_extract: energy
+energy_extract_conf:
+    fs: 48000
+    n_fft: 8192
+    hop_length: 1024
+    win_length: 4096
+    reduction_factor: 1
+energy_normalize: global_mvn
+energy_normalize_conf:
+    stats_file: exp/tts_stats_raw_char_None/train/energy_stats.npz
+required:
+- output_dir
+- token_list
+version: '202402'
+distributed: true

assamese_latest/female/model/energy_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e33101ff3538ca740f6c8fc35483fffab31722c9f0ae99adab07dd29c361de
+size 770

assamese_latest/female/model/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9b6ee7475d00198e08ea5b675f2cb5e81239a5f0babf83866b37b51ef2e0a1
+size 2042

assamese_latest/female/model/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5cd37cac859ad35acd2d0510fe3b4c5b388d167c9d70fb12efd1f5d0b03560
+size 152129434

assamese_latest/female/model/pitch_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dbac0bea459888e39a56f5f04e150d35a21f966e6e04b1d027c354e9de99aab
+size 770

assamese_latest/male/model/config.yaml

@@ -0,0 +1,315 @@
+accum_grad: 8
+adapter: lora
+adapter_conf: {}
+allow_multi_rates: false
+allow_variable_data_keys: false
+batch_bins: 3000000
+batch_size: 20
+batch_type: numel
+best_model_criterion:
+- - valid
+  - loss
+  - min
+- - train
+  - loss
+  - min
+bpemodel: null
+chunk_default_fs: null
+chunk_discard_short_samples: true
+chunk_excluded_key_prefixes: []
+chunk_length: 500
+chunk_max_abs_length: null
+chunk_shift_ratio: 0.5
+cleaner: null
+collect_stats: false
+config: conf/tuning/train_fastspeech2.yaml
+create_graph_in_tensorboard: false
+cudnn_benchmark: false
+cudnn_deterministic: true
+cudnn_enabled: true
+detect_anomaly: false
+dist_backend: nccl
+dist_init_method: env://
+dist_launcher: null
+dist_master_addr: localhost
+dist_master_port: 44409
+dist_rank: 0
+dist_world_size: 2
+distributed: true
+drop_last_iter: false
+dry_run: false
+early_stopping_criterion:
+- valid
+- loss
+- min
+energy_extract: energy
+energy_extract_conf:
+  fs: 48000
+  hop_length: 1024
+  n_fft: 8192
+  reduction_factor: 1
+  win_length: 4096
+energy_normalize: global_mvn
+energy_normalize_conf:
+  stats_file: /home/speech/Fastspeech2_HS/assamese_latest/male/model/energy_stats.npz
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+feats_extract: fbank
+feats_extract_conf:
+  fmax: 24000
+  fmin: 0
+  fs: 48000
+  hop_length: 1024
+  n_fft: 8192
+  n_mels: 160
+  win_length: 4096
+fold_length:
+- 150
+- 819200
+freeze_param: []
+g2p: null
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+ignore_init_mismatch: false
+init_param: []
+iterator_type: sequence
+keep_nbest_models: 5
+local_rank: 0
+log_interval: null
+log_level: INFO
+max_cache_fd: 32
+max_cache_size: 0.0
+max_epoch: 1000
+model_conf: {}
+multiple_iterator: false
+multiprocessing_distributed: true
+nbest_averaging_interval: 0
+ngpu: 1
+no_forward_run: false
+non_linguistic_symbols: null
+normalize: global_mvn
+normalize_conf:
+  stats_file: /home/speech/Fastspeech2_HS/assamese_latest/male/model/feats_stats.npz
+num_att_plot: 3
+num_cache_chunks: 1024
+num_iters_per_epoch: 800
+num_workers: 1
+odim: null
+optim: adam
+optim_conf:
+  lr: 1.0
+output_dir: exp/tts_train_fastspeech2_raw_char_None
+patience: null
+pitch_extract: dio
+pitch_extract_conf:
+  f0max: 350
+  f0min: 40
+  fs: 48000
+  hop_length: 1024
+  n_fft: 8192
+  reduction_factor: 1
+pitch_normalize: global_mvn
+pitch_normalize_conf:
+  stats_file: /home/speech/Fastspeech2_HS/assamese_latest/male/model/pitch_stats.npz
+pretrain_path: null
+print_config: false
+required:
+- output_dir
+- token_list
+resume: true
+save_strategy: all
+scheduler: noamlr
+scheduler_conf:
+  model_size: 384
+  warmup_steps: 4000
+seed: 0
+sharded_ddp: false
+shuffle_within_batch: false
+sort_batch: descending
+sort_in_batch: descending
+token_list:
+- <blank>
+- <unk>
+- <space>
+- $
+- ','
+- .
+- M
+- q
+- H
+- k
+- "\u0916"
+- g
+- "\u0918"
+- "\u0919"
+- c
+- C
+- j
+- J
+- "\u091E"
+- "\u091F"
+- "\u0920"
+- "\u0921"
+- "\u0922"
+- "\u0923"
+- t
+- "\u0925"
+- d
+- "\u0927"
+- n
+- "\u0929"
+- p
+- P
+- b
+- B
+- m
+- y
+- r
+- "\u0931"
+- l
+- "\u0D33"
+- Z
+- w
+- "\u0936"
+- "\u0937"
+- s
+- h
+- Y
+- "\u093D"
+- "\u0915"
+- K
+- G
+- z
+- D
+- T
+- f
+- "\u0960"
+- "\u0D7A"
+- N
+- "\u0D7C"
+- "\u0D7D"
+- "\u0D7E"
+- a
+- A
+- i
+- I
+- u
+- U
+- R
+- "\u090D"
+- e
+- E
+- "\u0910"
+- "\u0911"
+- o
+- O
+- "\u0914"
+- "\u0B89"
+- <sos/eos>
+token_type: char
+train_data_path_and_name_and_type:
+- - dump/raw/tr_no_dev/text
+  - text
+  - text
+- - duration_info/tr_no_dev/durations
+  - durations
+  - text_int
+- - dump/raw/tr_no_dev/wav.scp
+  - speech
+  - sound
+- - exp/tts_stats_raw_char_None/train/collect_feats/pitch.scp
+  - pitch
+  - npy
+- - exp/tts_stats_raw_char_None/train/collect_feats/energy.scp
+  - energy
+  - npy
+train_dtype: float32
+train_shape_file:
+- exp/tts_stats_raw_char_None/train/text_shape.char
+- exp/tts_stats_raw_char_None/train/speech_shape
+tts: fastspeech2
+tts_conf:
+  adim: 384
+  aheads: 2
+  decoder_normalize_before: true
+  dlayers: 4
+  dunits: 1536
+  duration_predictor_chans: 256
+  duration_predictor_kernel_size: 3
+  duration_predictor_layers: 2
+  elayers: 4
+  encoder_normalize_before: true
+  energy_embed_dropout: 0.0
+  energy_embed_kernel_size: 1
+  energy_predictor_chans: 256
+  energy_predictor_dropout: 0.5
+  energy_predictor_kernel_size: 3
+  energy_predictor_layers: 2
+  eunits: 1536
+  init_dec_alpha: 1.0
+  init_enc_alpha: 1.0
+  init_type: xavier_uniform
+  pitch_embed_dropout: 0.0
+  pitch_embed_kernel_size: 1
+  pitch_predictor_chans: 256
+  pitch_predictor_dropout: 0.5
+  pitch_predictor_kernel_size: 5
+  pitch_predictor_layers: 5
+  positionwise_conv_kernel_size: 3
+  positionwise_layer_type: conv1d
+  postnet_chans: 256
+  postnet_filts: 5
+  postnet_layers: 5
+  reduction_factor: 1
+  stop_gradient_from_energy_predictor: false
+  stop_gradient_from_pitch_predictor: true
+  transformer_dec_attn_dropout_rate: 0.2
+  transformer_dec_dropout_rate: 0.2
+  transformer_dec_positional_dropout_rate: 0.2
+  transformer_enc_attn_dropout_rate: 0.2
+  transformer_enc_dropout_rate: 0.2
+  transformer_enc_positional_dropout_rate: 0.2
+  use_masking: true
+  use_scaled_pos_enc: true
+unused_parameters: false
+use_adapter: false
+use_amp: false
+use_matplotlib: true
+use_preprocessor: true
+use_tensorboard: true
+use_wandb: false
+val_scheduler_criterion:
+- valid
+- loss
+valid_batch_bins: null
+valid_batch_size: null
+valid_batch_type: null
+valid_data_path_and_name_and_type:
+- - dump/raw/dev/text
+  - text
+  - text
+- - duration_info/dev/durations
+  - durations
+  - text_int
+- - dump/raw/dev/wav.scp
+  - speech
+  - sound
+- - exp/tts_stats_raw_char_None/valid/collect_feats/pitch.scp
+  - pitch
+  - npy
+- - exp/tts_stats_raw_char_None/valid/collect_feats/energy.scp
+  - energy
+  - npy
+valid_iterator_type: null
+valid_max_cache_size: null
+valid_shape_file:
+- exp/tts_stats_raw_char_None/valid/text_shape.char
+- exp/tts_stats_raw_char_None/valid/speech_shape
+version: '202402'
+wandb_entity: null
+wandb_id: null
+wandb_model_log_interval: -1
+wandb_name: null
+wandb_project: null
+write_collected_feats: false

assamese_latest/male/model/energy_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a64d5dd4ee24ad1b403ad07911b9e30f4d482f97c331b844272725617fb941a6
+size 770

assamese_latest/male/model/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbb77de18a76f7e991b256a042acc361aa338498daa52048978ea050a9fd528
+size 2042

assamese_latest/male/model/feats_type

@@ -0,0 +1 @@
+raw

assamese_latest/male/model/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f52c3b1c4edd258dbd9e46920896bc0215cfe5c78957e3ee2a25de6f3ef916b
+size 152128410

assamese_latest/male/model/pitch_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47de3b8ee9c740a5f24ceafcbe9b3486dfd4b3676d95282d7ce97c1116d834fd
+size 770

bengali_latest/male/model/config.yaml

@@ -0,0 +1,315 @@
+accum_grad: 8
+adapter: lora
+adapter_conf: {}
+allow_multi_rates: false
+allow_variable_data_keys: false
+batch_bins: 3000000
+batch_size: 20
+batch_type: numel
+best_model_criterion:
+- - valid
+  - loss
+  - min
+- - train
+  - loss
+  - min
+bpemodel: null
+chunk_default_fs: null
+chunk_discard_short_samples: true
+chunk_excluded_key_prefixes: []
+chunk_length: 500
+chunk_max_abs_length: null
+chunk_shift_ratio: 0.5
+cleaner: null
+collect_stats: false
+config: conf/tuning/train_fastspeech2.yaml
+create_graph_in_tensorboard: false
+cudnn_benchmark: false
+cudnn_deterministic: true
+cudnn_enabled: true
+detect_anomaly: false
+dist_backend: nccl
+dist_init_method: env://
+dist_launcher: null
+dist_master_addr: localhost
+dist_master_port: 38255
+dist_rank: 0
+dist_world_size: 2
+distributed: true
+drop_last_iter: false
+dry_run: false
+early_stopping_criterion:
+- valid
+- loss
+- min
+energy_extract: energy
+energy_extract_conf:
+  fs: 48000
+  hop_length: 1024
+  n_fft: 8192
+  reduction_factor: 1
+  win_length: 4096
+energy_normalize: global_mvn
+energy_normalize_conf:
+  stats_file: /home/speech/Fastspeech2_latest models/Fastspeech2_HS/bengali_latest/male/model/energy_stats.npz
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+feats_extract: fbank
+feats_extract_conf:
+  fmax: 24000
+  fmin: 0
+  fs: 48000
+  hop_length: 1024
+  n_fft: 8192
+  n_mels: 160
+  win_length: 4096
+fold_length:
+- 150
+- 819200
+freeze_param: []
+g2p: null
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+ignore_init_mismatch: false
+init_param: []
+iterator_type: sequence
+keep_nbest_models: 5
+local_rank: 0
+log_interval: null
+log_level: INFO
+max_cache_fd: 32
+max_cache_size: 0.0
+max_epoch: 1000
+model_conf: {}
+multiple_iterator: false
+multiprocessing_distributed: true
+nbest_averaging_interval: 0
+ngpu: 1
+no_forward_run: false
+non_linguistic_symbols: null
+normalize: global_mvn
+normalize_conf:
+  stats_file: /home/speech/Fastspeech2_latest models/Fastspeech2_HS/bengali_latest/male/model/feats_stats.npz
+num_att_plot: 3
+num_cache_chunks: 1024
+num_iters_per_epoch: 800
+num_workers: 1
+odim: null
+optim: adam
+optim_conf:
+  lr: 1.0
+output_dir: exp/tts_train_fastspeech2_raw_char_None
+patience: null
+pitch_extract: dio
+pitch_extract_conf:
+  f0max: 350
+  f0min: 40
+  fs: 48000
+  hop_length: 1024
+  n_fft: 8192
+  reduction_factor: 1
+pitch_normalize: global_mvn
+pitch_normalize_conf:
+  stats_file: /home/speech/Fastspeech2_latest models/Fastspeech2_HS/bengali_latest/male/model/pitch_stats.npz
+pretrain_path: null
+print_config: false
+required:
+- output_dir
+- token_list
+resume: true
+save_strategy: all
+scheduler: noamlr
+scheduler_conf:
+  model_size: 384
+  warmup_steps: 4000
+seed: 0
+sharded_ddp: false
+shuffle_within_batch: false
+sort_batch: descending
+sort_in_batch: descending
+token_list:
+- <blank>
+- <unk>
+- <space>
+- $
+- ','
+- .
+- M
+- q
+- H
+- k
+- "\u0916"
+- g
+- "\u0918"
+- "\u0919"
+- c
+- C
+- j
+- J
+- "\u091E"
+- "\u091F"
+- "\u0920"
+- "\u0921"
+- "\u0922"
+- "\u0923"
+- t
+- "\u0925"
+- d
+- "\u0927"
+- n
+- "\u0929"
+- p
+- P
+- b
+- B
+- m
+- y
+- r
+- "\u0931"
+- l
+- "\u0D33"
+- Z
+- w
+- "\u0936"
+- "\u0937"
+- s
+- h
+- Y
+- "\u093D"
+- "\u0915"
+- K
+- G
+- z
+- D
+- T
+- f
+- "\u0960"
+- "\u0D7A"
+- N
+- "\u0D7C"
+- "\u0D7D"
+- "\u0D7E"
+- a
+- A
+- i
+- I
+- u
+- U
+- R
+- "\u090D"
+- e
+- E
+- "\u0910"
+- "\u0911"
+- o
+- O
+- "\u0914"
+- "\u0B89"
+- <sos/eos>
+token_type: char
+train_data_path_and_name_and_type:
+- - dump/raw/tr_no_dev/text
+  - text
+  - text
+- - duration_info/tr_no_dev/durations
+  - durations
+  - text_int
+- - dump/raw/tr_no_dev/wav.scp
+  - speech
+  - sound
+- - exp/tts_stats_raw_char_None/train/collect_feats/pitch.scp
+  - pitch
+  - npy
+- - exp/tts_stats_raw_char_None/train/collect_feats/energy.scp
+  - energy
+  - npy
+train_dtype: float32
+train_shape_file:
+- exp/tts_stats_raw_char_None/train/text_shape.char
+- exp/tts_stats_raw_char_None/train/speech_shape
+tts: fastspeech2
+tts_conf:
+  adim: 384
+  aheads: 2
+  decoder_normalize_before: true
+  dlayers: 4
+  dunits: 1536
+  duration_predictor_chans: 256
+  duration_predictor_kernel_size: 3
+  duration_predictor_layers: 2
+  elayers: 4
+  encoder_normalize_before: true
+  energy_embed_dropout: 0.0
+  energy_embed_kernel_size: 1
+  energy_predictor_chans: 256
+  energy_predictor_dropout: 0.5
+  energy_predictor_kernel_size: 3
+  energy_predictor_layers: 2
+  eunits: 1536
+  init_dec_alpha: 1.0
+  init_enc_alpha: 1.0
+  init_type: xavier_uniform
+  pitch_embed_dropout: 0.0
+  pitch_embed_kernel_size: 1
+  pitch_predictor_chans: 256
+  pitch_predictor_dropout: 0.5
+  pitch_predictor_kernel_size: 5
+  pitch_predictor_layers: 5
+  positionwise_conv_kernel_size: 3
+  positionwise_layer_type: conv1d
+  postnet_chans: 256
+  postnet_filts: 5
+  postnet_layers: 5
+  reduction_factor: 1
+  stop_gradient_from_energy_predictor: false
+  stop_gradient_from_pitch_predictor: true
+  transformer_dec_attn_dropout_rate: 0.2
+  transformer_dec_dropout_rate: 0.2
+  transformer_dec_positional_dropout_rate: 0.2
+  transformer_enc_attn_dropout_rate: 0.2
+  transformer_enc_dropout_rate: 0.2
+  transformer_enc_positional_dropout_rate: 0.2
+  use_masking: true
+  use_scaled_pos_enc: true
+unused_parameters: false
+use_adapter: false
+use_amp: false
+use_matplotlib: true
+use_preprocessor: true
+use_tensorboard: true
+use_wandb: false
+val_scheduler_criterion:
+- valid
+- loss
+valid_batch_bins: null
+valid_batch_size: null
+valid_batch_type: null
+valid_data_path_and_name_and_type:
+- - dump/raw/dev/text
+  - text
+  - text
+- - duration_info/dev/durations
+  - durations
+  - text_int
+- - dump/raw/dev/wav.scp
+  - speech
+  - sound
+- - exp/tts_stats_raw_char_None/valid/collect_feats/pitch.scp
+  - pitch
+  - npy
+- - exp/tts_stats_raw_char_None/valid/collect_feats/energy.scp
+  - energy
+  - npy
+valid_iterator_type: null
+valid_max_cache_size: null
+valid_shape_file:
+- exp/tts_stats_raw_char_None/valid/text_shape.char
+- exp/tts_stats_raw_char_None/valid/speech_shape
+version: '202402'
+wandb_entity: null
+wandb_id: null
+wandb_model_log_interval: -1
+wandb_name: null
+wandb_project: null
+write_collected_feats: false

bengali_latest/male/model/energy_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0ff72de15d28f934bf95054d8c82210dbfdbe9114780b92f536a4cfd908358
+size 770

bengali_latest/male/model/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63bfa54c96d7998cc22e479118fb7be8a5a9a1fae9508c210fd3f00065e0945
+size 2042

bengali_latest/male/model/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e131b107524777db0ae4f2578856b9baba42c2ed944433c7d5a086c56f0973e8
+size 152128410

bengali_latest/male/model/pitch_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508206b876c66ec155e6473527155c24ed06d65f8a23963e5bec908a27be018f
+size 770

bodo_latest/female/model/config.yaml

@@ -0,0 +1,319 @@
+config: conf/tuning/train_fastspeech2.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/tts_train_fastspeech2_raw_char_None
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 2
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 40847
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: false
+sharded_ddp: false
+use_deepspeed: false
+deepspeed_config: null
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 1000
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+-   - train
+    - loss
+    - min
+keep_nbest_models: 5
+nbest_averaging_interval: 0
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 8
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+use_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 800
+batch_size: 20
+valid_batch_size: null
+batch_bins: 3000000
+valid_batch_bins: null
+train_shape_file:
+- exp/tts_stats_raw_char_None/train/text_shape.char
+- exp/tts_stats_raw_char_None/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_char_None/valid/text_shape.char
+- exp/tts_stats_raw_char_None/valid/speech_shape
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+- 819200
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: null
+chunk_max_abs_length: null
+chunk_discard_short_samples: true
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_no_dev/text
+    - text
+    - text
+-   - duration_info/tr_no_dev/durations
+    - durations
+    - text_int
+-   - dump/raw/tr_no_dev/wav.scp
+    - speech
+    - sound
+-   - exp/tts_stats_raw_char_None/train/collect_feats/pitch.scp
+    - pitch
+    - npy
+-   - exp/tts_stats_raw_char_None/train/collect_feats/energy.scp
+    - energy
+    - npy
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/text
+    - text
+    - text
+-   - duration_info/dev/durations
+    - durations
+    - text_int
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - exp/tts_stats_raw_char_None/valid/collect_feats/pitch.scp
+    - pitch
+    - npy
+-   - exp/tts_stats_raw_char_None/valid/collect_feats/energy.scp
+    - energy
+    - npy
+multi_task_dataset: false
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: false
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 1.0
+scheduler: noamlr
+scheduler_conf:
+    model_size: 384
+    warmup_steps: 4000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- $
+- ','
+- .
+- M
+- q
+- H
+- k
+- ख
+- g
+- घ
+- ङ
+- c
+- C
+- j
+- J
+- ञ
+- ट
+- ठ
+- ड
+- ढ
+- ण
+- t
+- थ
+- d
+- ध
+- n
+- ऩ
+- p
+- P
+- b
+- B
+- m
+- y
+- r
+- ऱ
+- l
+- ള
+- Z
+- w
+- श
+- ष
+- s
+- h
+- Y
+- ऽ
+- क
+- K
+- G
+- z
+- D
+- T
+- f
+- ॠ
+- ൺ
+- N
+- ർ
+- ൽ
+- ൾ
+- a
+- A
+- i
+- I
+- u
+- U
+- R
+- ऍ
+- e
+- E
+- ऐ
+- ऑ
+- o
+- O
+- औ
+- உ
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+feats_extract: fbank
+feats_extract_conf:
+    n_fft: 8192
+    hop_length: 1024
+    win_length: 4096
+    fs: 48000
+    fmin: 0
+    fmax: 24000
+    n_mels: 160
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/tts_stats_raw_char_None/train/feats_stats.npz
+tts: fastspeech2
+tts_conf:
+    adim: 384
+    aheads: 2
+    elayers: 4
+    eunits: 1536
+    dlayers: 4
+    dunits: 1536
+    positionwise_layer_type: conv1d
+    positionwise_conv_kernel_size: 3
+    duration_predictor_layers: 2
+    duration_predictor_chans: 256
+    duration_predictor_kernel_size: 3
+    postnet_layers: 5
+    postnet_filts: 5
+    postnet_chans: 256
+    use_masking: true
+    use_scaled_pos_enc: true
+    encoder_normalize_before: true
+    decoder_normalize_before: true
+    reduction_factor: 1
+    init_type: xavier_uniform
+    init_enc_alpha: 1.0
+    init_dec_alpha: 1.0
+    transformer_enc_dropout_rate: 0.2
+    transformer_enc_positional_dropout_rate: 0.2
+    transformer_enc_attn_dropout_rate: 0.2
+    transformer_dec_dropout_rate: 0.2
+    transformer_dec_positional_dropout_rate: 0.2
+    transformer_dec_attn_dropout_rate: 0.2
+    pitch_predictor_layers: 5
+    pitch_predictor_chans: 256
+    pitch_predictor_kernel_size: 5
+    pitch_predictor_dropout: 0.5
+    pitch_embed_kernel_size: 1
+    pitch_embed_dropout: 0.0
+    stop_gradient_from_pitch_predictor: true
+    energy_predictor_layers: 2
+    energy_predictor_chans: 256
+    energy_predictor_kernel_size: 3
+    energy_predictor_dropout: 0.5
+    energy_embed_kernel_size: 1
+    energy_embed_dropout: 0.0
+    stop_gradient_from_energy_predictor: false
+pitch_extract: dio
+pitch_extract_conf:
+    fs: 48000
+    n_fft: 8192
+    hop_length: 1024
+    f0max: 400
+    f0min: 80
+    reduction_factor: 1
+pitch_normalize: global_mvn
+pitch_normalize_conf:
+    stats_file: exp/tts_stats_raw_char_None/train/pitch_stats.npz
+energy_extract: energy
+energy_extract_conf:
+    fs: 48000
+    n_fft: 8192
+    hop_length: 1024
+    win_length: 4096
+    reduction_factor: 1
+energy_normalize: global_mvn
+energy_normalize_conf:
+    stats_file: exp/tts_stats_raw_char_None/train/energy_stats.npz
+required:
+- output_dir
+- token_list
+version: '202402'
+distributed: true

bodo_latest/female/model/energy_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f146e38995c250d297602ef8ae9a86ca151b5dbd85bd2a0c6d6fc480958825c6
+size 770

bodo_latest/female/model/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac92ccb722a0ed041407e19bddde97f055e37d1108c2927c573f912b281e9f6
+size 2042

bodo_latest/female/model/feats_type

@@ -0,0 +1 @@
+raw

bodo_latest/female/model/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7e1023281d3358bca078b2a218cddda8fc79aef7f0e3d47272331b8bf9645a
+size 152129434

bodo_latest/female/model/pitch_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59051dd33e6f33a98737cbe4a5a220eb9af37c43d2b660f3d257f411f1128025
+size 770

bodo_latest/male/model/config.yaml

@@ -0,0 +1,319 @@
+config: conf/tuning/train_fastspeech2.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/tts_train_fastspeech2_raw_char_None
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 2
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 53925
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: false
+sharded_ddp: false
+use_deepspeed: false
+deepspeed_config: null
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 1000
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+-   - train
+    - loss
+    - min
+keep_nbest_models: 5
+nbest_averaging_interval: 0
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 8
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+use_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 800
+batch_size: 20
+valid_batch_size: null
+batch_bins: 3000000
+valid_batch_bins: null
+train_shape_file:
+- exp/tts_stats_raw_char_None/train/text_shape.char
+- exp/tts_stats_raw_char_None/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_char_None/valid/text_shape.char
+- exp/tts_stats_raw_char_None/valid/speech_shape
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+- 819200
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: null
+chunk_max_abs_length: null
+chunk_discard_short_samples: true
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_no_dev/text
+    - text
+    - text
+-   - duration_info/tr_no_dev/durations
+    - durations
+    - text_int
+-   - dump/raw/tr_no_dev/wav.scp
+    - speech
+    - sound
+-   - exp/tts_stats_raw_char_None/train/collect_feats/pitch.scp
+    - pitch
+    - npy
+-   - exp/tts_stats_raw_char_None/train/collect_feats/energy.scp
+    - energy
+    - npy
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/text
+    - text
+    - text
+-   - duration_info/dev/durations
+    - durations
+    - text_int
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - exp/tts_stats_raw_char_None/valid/collect_feats/pitch.scp
+    - pitch
+    - npy
+-   - exp/tts_stats_raw_char_None/valid/collect_feats/energy.scp
+    - energy
+    - npy
+multi_task_dataset: false
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: false
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 1.0
+scheduler: noamlr
+scheduler_conf:
+    model_size: 384
+    warmup_steps: 4000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- $
+- ','
+- .
+- M
+- q
+- H
+- k
+- ख
+- g
+- घ
+- ङ
+- c
+- C
+- j
+- J
+- ञ
+- ट
+- ठ
+- ड
+- ढ
+- ण
+- t
+- थ
+- d
+- ध
+- n
+- ऩ
+- p
+- P
+- b
+- B
+- m
+- y
+- r
+- ऱ
+- l
+- ള
+- Z
+- w
+- श
+- ष
+- s
+- h
+- Y
+- ऽ
+- क
+- K
+- G
+- z
+- D
+- T
+- f
+- ॠ
+- ൺ
+- N
+- ർ
+- ൽ
+- ൾ
+- a
+- A
+- i
+- I
+- u
+- U
+- R
+- ऍ
+- e
+- E
+- ऐ
+- ऑ
+- o
+- O
+- औ
+- உ
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+feats_extract: fbank
+feats_extract_conf:
+    n_fft: 8192
+    hop_length: 1024
+    win_length: 4096
+    fs: 48000
+    fmin: 0
+    fmax: 24000
+    n_mels: 160
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/tts_stats_raw_char_None/train/feats_stats.npz
+tts: fastspeech2
+tts_conf:
+    adim: 384
+    aheads: 2
+    elayers: 4
+    eunits: 1536
+    dlayers: 4
+    dunits: 1536
+    positionwise_layer_type: conv1d
+    positionwise_conv_kernel_size: 3
+    duration_predictor_layers: 2
+    duration_predictor_chans: 256
+    duration_predictor_kernel_size: 3
+    postnet_layers: 5
+    postnet_filts: 5
+    postnet_chans: 256
+    use_masking: true
+    use_scaled_pos_enc: true
+    encoder_normalize_before: true
+    decoder_normalize_before: true
+    reduction_factor: 1
+    init_type: xavier_uniform
+    init_enc_alpha: 1.0
+    init_dec_alpha: 1.0
+    transformer_enc_dropout_rate: 0.2
+    transformer_enc_positional_dropout_rate: 0.2
+    transformer_enc_attn_dropout_rate: 0.2
+    transformer_dec_dropout_rate: 0.2
+    transformer_dec_positional_dropout_rate: 0.2
+    transformer_dec_attn_dropout_rate: 0.2
+    pitch_predictor_layers: 5
+    pitch_predictor_chans: 256
+    pitch_predictor_kernel_size: 5
+    pitch_predictor_dropout: 0.5
+    pitch_embed_kernel_size: 1
+    pitch_embed_dropout: 0.0
+    stop_gradient_from_pitch_predictor: true
+    energy_predictor_layers: 2
+    energy_predictor_chans: 256
+    energy_predictor_kernel_size: 3
+    energy_predictor_dropout: 0.5
+    energy_embed_kernel_size: 1
+    energy_embed_dropout: 0.0
+    stop_gradient_from_energy_predictor: false
+pitch_extract: dio
+pitch_extract_conf:
+    fs: 48000
+    n_fft: 8192
+    hop_length: 1024
+    f0max: 350
+    f0min: 40
+    reduction_factor: 1
+pitch_normalize: global_mvn
+pitch_normalize_conf:
+    stats_file: exp/tts_stats_raw_char_None/train/pitch_stats.npz
+energy_extract: energy
+energy_extract_conf:
+    fs: 48000
+    n_fft: 8192
+    hop_length: 1024
+    win_length: 4096
+    reduction_factor: 1
+energy_normalize: global_mvn
+energy_normalize_conf:
+    stats_file: exp/tts_stats_raw_char_None/train/energy_stats.npz
+required:
+- output_dir
+- token_list
+version: '202402'
+distributed: true

bodo_latest/male/model/energy_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ccfd0ab92010376d6cecbf0d2d3e2e338ccb2cc1a4c44af9acd1f9bd569f9e
+size 770

bodo_latest/male/model/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0adb54c43f773f5c078a60c30cfba90f4b3cb02461ac3a4f9cbc638f91e2e82
+size 2042

bodo_latest/male/model/feats_type

@@ -0,0 +1 @@
+raw

bodo_latest/male/model/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:742c513ae2866449704836faeeedb4c4e6c364a4e4d0f9ebc96f234efc084b8d
+size 152129434

bodo_latest/male/model/pitch_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a143913223f17d10f677a7b94e26ccf8d1251ff97d882fe65f33542a3d5722
+size 770

charmap/Text_Cleaning.ipynb

@@ -0,0 +1,332 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "############################################################\n",
+    "#Author : Bhagyashree\n",
+    "#Date : 1st Sept, 2020\n",
+    "#Purpose : Text Cleaning\n",
+    "#Input : Text file after timestamp removal\n",
+    "#Output : Text file after cleaning data\n",
+    "############################################################"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import nltk\n",
+    "import numpy\n",
+    "import xlrd\n",
+    "import openpyxl \n",
+    "import re"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "अब हम  ऑलट्रेशन ऑफ मेमोरेंडम  के बारे में बात करेंगे।\n",
+      " मेमोरेंडम के विषयों को बदल दिया जा सकता है।\n",
+      "कंपनी अधिनियम 1956 के तहत\n",
+      "निम्नलिखित प्रक्रिया के अनुसार\n",
+      "यदि कोई कंपनी अपना नाम बदलना चाहती है,\n",
+      "तो वे विशेष संकल्प में ऐसा कर सकती है।\n",
+      "और केंद्र सरकार की मंजूरी के साथ\n",
+      "लिखित में\n",
+      "हालाँकि, ऐसी किसी भी मंजूरी की आवश्यकता नहीं होती है\n",
+      "केवल कंपनी के नाम में परिवर्तन के लिए\n",
+      "बल्कि यह प्रक्रिया\n",
+      "पूरी तरह से निजी शब्द को हटाने के लिए होती है।\n",
+      "तो इस मामले में\n",
+      "एक सार्वजनिक कंपनी को एक निजी कंपनी के संबंध में,\n",
+      "या एक निजी कंपनी को एक सार्वजनिक कंपनी में परिवर्तित करने\n",
+      "दूसरी जगह पर पंजीकृत कार्यालय का दोबारा परिवर्तन किया जाना है\n",
+      "अगर एक ही शहर, कस्बे\n",
+      "या गाँव में एक जगह से\n",
+      "30 दिनों का नोटिस दिया जाना होता है।\n",
+      "यह रजिस्ट्रार द्वारा परिवर्तन की तिथि के बाद\n",
+      "होगा जो उसी को दर्ज करेगा।\n",
+      "पंजीकृत कार्यालय के परिवर्तन के मामले में\n",
+      "जबकि एक ही राज्य में 1 शहर से दूसरे शहर में,\n",
+      "विशेष प्रस्ताव पारित किया जाना आवश्यक है।\n",
+      "शेयरधारकों की आम बैठक में\n",
+      "और इसकी एक प्रति रजिस्ट्रार के पास कार्यालय को\n",
+      "30 दिनों के भीतर बदलने के दाखिल करनी होगी।\n",
+      "नोटिस देना होगा।\n",
+      "रजिस्ट्रार को कार्यालय के नये पते का\n",
+      "तब तक परिवर्तन प्रभावी नहीं होगा।\n",
+      "जब तक केंद्र सरकार द्वारा प्रस्ताव की पुष्टि नहीं हो जाती\n",
+      "कंपनी किसी भी आधार पर\n",
+      "उपधारा 1 से\n",
+      "उपधारा 7 में धारा 17 तक उल्लेखित है।\n",
+      "जैसा कि अधिनियम के बाद ही परिवर्तन प्रभावी होगा।\n",
+      "अपने उद्देश्यों में बदलाव कर सकती है\n",
+      "सामान्य बैठक में सदस्यों द्वारा\n",
+      "कंपनी संशोधन अधिनियम 1996 को मेमोरेंडम ऑफ एसोसिएशन के\n",
+      "केंद्र सरकार के प्रतिबंध के साथ समाप्त कर दिया गया है।\n",
+      "विशेष संकल्प के अनुरूप अनुमोदित किए जाने\n",
+      "ऑब्जेक्ट क्लॉज में परिवर्तन के प्रति शेयर पूंजी में\n",
+      "परिवर्तन की प्रक्रिया और ऐसे परिवर्तन करने के अधिकार।\n",
+      "समान्य पहलु को  आर्टीकल ऑफ एसोसिएशन  में रखा गया है।\n",
+      "यदि  संबंधित विषय के\n",
+      " आर्टीकल ऑफ एसोसिएशन  में पीछे की प्रक्रिया नहीं दी गई है।\n",
+      "कंपनी को पारित करके आर्टीकल ऑफ एसोसिएशन को बदलना होगा।\n",
+      "एक विशेष प्रस्ताव\n",
+      "अब, हम ऑलट्रेशन ऑफ पर चर्चा करेंगे।\n",
+      "कंपनी अधिनियम 2013 के तहत  मेमोरेंडम\n",
+      "अधिनियम की धारा 16, 17, 18, 19,\n",
+      "1956 के कंपनी 21, 23 और 37 के अनुरूप।\n",
+      "कंपनी अधिनियम, 2013 की धारा 13 ने\n",
+      "  ऑलट्रेशन ऑफ मेमोरेंडम  के लिए मानदंड निर्धारित किए हैं।\n",
+      "यह वही वर्णन करता है कि जैसा कि धारा 61 में दिया गया है।\n",
+      "एक कंपनी विशेष संकल्प द्वारा\n",
+      "और  प्रावधानों को बदल सकती है।\n",
+      "निर्दिष्ट प्रक्रिया के अनुपालन से मेमोरेंडम\n",
+      "नाम खंड के परिवर्तन के संबंध में,\n",
+      "कंपनी अपना नाम बदल सकती है।\n",
+      "अनुमोदन के बाद लिखित रूप में केंद्र सरकार द्वारा\n",
+      "इसलिए जब कंपनी के नाम में कोई बदलाव किया जाता है,\n",
+      "रजिस्टर में दर्ज करेगा।\n",
+      " तो रजिस्ट्रार कंपनी के नया नाम\n",
+      "पुराने नाम के स्थान पर\n",
+      "निगमन का एक नया प्रमाणपत्र जारी करेगा।\n",
+      "कंपनी के पंजीकृत कार्यालय के बारे में\n",
+      "जैसा कि पहले उल्लेख किया गया है,\n",
+      "तब तक कोई प्रभाव नहीं पड़ेगा जब तक कि वह केंद्र सरकार द्वारा अनुमोदित नहीं हो जाता।\n",
+      "ऑब्जेक्ट क्लॉज के किसी भी परिवर्तन के संबंध में,\n",
+      "किसी कंपनी के  मेमोरेंडम  के\n",
+      "रजिस्ट्रार को दाखिल करने की\n",
+      "30 दिनों की अवधि के भीतर\n",
+      "तारीख से पंजीकरण को प्रमाणित करना होता है।\n",
+      "इस विशेष प्रस्ताव खंड के उप खंड 6 के खंड A के अनुसार\n",
+      "चलिए फिर से संक्षेप में\n",
+      " ऑलट्रेशन ऑफ मेमोरेंडम के महत्व के बारे में चर्चा करते हैं\n",
+      " क्योंकि ये इस मॉड्यूल के अध्ययन का एक बहुत महत्वपूर्ण हिस्सा है।\n",
+      "पहला महत्व यह है\n",
+      "कि यह एक बहुत ही आवश्यक दस्तावेज है।\n",
+      "एक कंपनी के निगमन के लिए\n",
+      "दूसरा, यह कंपनी के पंजीकृत कार्यालय को निर्दिष्ट करते हुए\n",
+      "रजिस्ट्रार और अदालत के अधिकार क्षेत्र को निर्धारित करता है।\n",
+      "तीसरा, यह कंपनी के अधिकारों में उद्देश्यों को\n",
+      "जनता की जानकारी के लिए दर्ज करता है।\n",
+      "अगला, यह कंपनी को केवल उन कृत्यों को करने के लिए\n",
+      "बाध्य करता है जो कंपनी के ऑब्जेक्ट क्लॉज में शामिल हैं।\n",
+      "यह कंपनी की अधिकृत कैपिटल\n",
+      "और उसके विभाजन को निश्चित राशि के शेयरों में निर्दिष्ट करता है।\n",
+      "पर प्रकाश डालता है।\n",
+      "यह कंपनी के सदस्यों के लायबिलिटी\n",
+      "अंत में, संघ के नियमों को\n",
+      "यह एक कंपनी के भी नियंत्रित करता है।\n"
+     ]
+    }
+   ],
+   "source": [
+    "file1 = open(\"recent_deliverables_dec2020/Corporate_Law/Hindi/ankita objects 02_Hindi_new.txt\",\"r+\",encoding='utf-8') \n",
+    "data = file1.read()\n",
+    "print(data)\n",
+    "file1.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "अब हम ऑलट्रेशन ऑफ मेमोरेंडम के बारे में बात करेंगे\n",
+      " मेमोरेंडम के विषयों को बदल दिया जा सकता है\n",
+      "कंपनी अधिनियम  वन  नाइन  फाइव   सिक्स  के तहत\n",
+      "निम्नलिखित प्रक्रिया के अनुसार\n",
+      "यदि कोई कंपनी अपना नाम बदलना चाहती है\n",
+      "तो वे विशेष संकल्प में ऐसा कर सकती है\n",
+      "और केंद्र सरकार की मंजूरी के साथ\n",
+      "लिखित में\n",
+      "हालाँकि ऐसी किसी भी मंजूरी की आवश्यकता नहीं होती है\n",
+      "केवल कंपनी के नाम में परिवर्तन के लिए\n",
+      "बल्कि यह प्रक्रिया\n",
+      "पूरी तरह से निजी शब्द को हटाने के लिए होती है\n",
+      "तो इस मामले में\n",
+      "एक सार्वजनिक कंपनी को एक निजी कंपनी के संबंध में\n",
+      "या एक निजी कंपनी को एक सार्वजनिक कंपनी में परिवर्तित करने\n",
+      "दूसरी जगह पर पंजीकृत कार्यालय का दोबारा परिवर्तन किया जाना है\n",
+      "अगर एक ही शहर कस्बे\n",
+      "या गाँव में एक जगह से\n",
+      " थ्री  ज़ीरो  दिनों का नोटिस दिया जाना होता है\n",
+      "यह रजिस्ट्रार द्वारा परिवर्तन की तिथि के बाद\n",
+      "होगा जो उसी को दर्ज करेगा\n",
+      "पंजीकृत कार्यालय के परिवर्तन के मामले में\n",
+      "जबकि एक ही राज्य में  वन  शहर से दूसरे शहर में\n",
+      "विशेष प्रस्ताव पारित किया जाना आवश्यक है\n",
+      "शेयरधारकों की आम बैठक में\n",
+      "और इसकी एक प्रति रजिस्ट्रार के पास कार्यालय को\n",
+      " थ्री  ज़ीरो  दिनों के भीतर बदलने के दाखिल करनी होगी\n",
+      "नोटिस देना होगा\n",
+      "रजिस्ट्रार को कार्यालय के नये पते का\n",
+      "तब तक परिवर्तन प्रभावी नहीं होगा\n",
+      "जब तक केंद्र सरकार द्वारा प्रस्ताव की पुष्टि नहीं हो जा���ी\n",
+      "कंपनी किसी भी आधार पर\n",
+      "उपधारा  वन  से\n",
+      "उपधारा  सेवेन  में धारा  वन  सेवेन  तक उल्लेखित है\n",
+      "जैसा कि अधिनियम के बाद ही परिवर्तन प्रभावी होगा\n",
+      "अपने उद्देश्यों में बदलाव कर सकती है\n",
+      "सामान्य बैठक में सदस्यों द्वारा\n",
+      "कंपनी संशोधन अधिनियम  वन  नाइन  नाइन  सिक्स  को मेमोरेंडम ऑफ एसोसिएशन के\n",
+      "केंद्र सरकार के प्रतिबंध के साथ समाप्त कर दिया गया है\n",
+      "विशेष संकल्प के अनुरूप अनुमोदित किए जाने\n",
+      "ऑब्जेक्ट क्लॉज में परिवर्तन के प्रति शेयर पूंजी में\n",
+      "परिवर्तन की प्रक्रिया और ऐसे परिवर्तन करने के अधिकार\n",
+      "समान्य पहलु को आर्टीकल ऑफ एसोसिएशन में रखा गया है\n",
+      "यदि संबंधित विषय के\n",
+      " आर्टीकल ऑफ एसोसिएशन में पीछे की प्रक्रिया नहीं दी गई है\n",
+      "कंपनी को पारित करके आर्टीकल ऑफ एसोसिएशन को बदलना होगा\n",
+      "एक विशेष प्रस्ताव\n",
+      "अब हम ऑलट्रेशन ऑफ पर चर्चा करेंगे\n",
+      "कंपनी अधिनियम  टू  ज़ीरो  वन  थ्री  के तहत मेमोरेंडम\n",
+      "अधिनियम की धारा  वन  सिक्स   वन  सेवेन   वन  ऐइट   वन  नाइन \n",
+      " वन  नाइन  फाइव   सिक्स  के कंपनी  टू  वन   टू  थ्री  और  थ्री  सेवेन  के अनुरूप\n",
+      "कंपनी अधिनियम  टू  ज़ीरो  वन  थ्री  की धारा  वन  थ्री  ने\n",
+      " ऑलट्रेशन ऑफ मेमोरेंडम के लिए मानदंड निर्धारित किए हैं\n",
+      "यह वही वर्णन करता है कि जैसा कि धारा  सिक्स  वन  में दिया गया है\n",
+      "एक कंपनी विशेष संकल्प द्वारा\n",
+      "और प्रावधानों को बदल सकती है\n",
+      "निर्दिष्ट प्रक्रिया के अनुपालन से मेमोरेंडम\n",
+      "नाम खंड के परिवर्तन के संबंध में\n",
+      "कंपनी अपना नाम बदल सकती है\n",
+      "अनुमोदन के बाद लिखित रूप में केंद्र सरकार द्वारा\n",
+      "इसलिए जब कंपनी के नाम में कोई बदलाव किया जाता है\n",
+      "रजिस्टर में दर्ज करेगा\n",
+      " तो रजिस्ट्रार कंपनी के नया नाम\n",
+      "पुराने नाम के स्थान पर\n",
+      "निगमन का एक नया प्रमाणपत्र जारी करेगा\n",
+      "कंपनी के पंजीकृत कार्यालय के बारे में\n",
+      "जैसा कि पहले उल्लेख किया गया है\n",
+      "तब तक कोई प्रभाव नहीं पड़ेगा जब तक कि वह केंद्र सरकार द्वारा अनुमोदित नहीं हो जाता\n",
+      "ऑब्जेक्ट क्लॉज के किसी भी परिवर्तन के संबंध में\n",
+      "किसी कंपनी के मेमोरेंडम के\n",
+      "रजिस्ट्रार को दाखिल करने की\n",
+      " थ्री  ज़ीरो  दिनों की अवधि के भीतर\n",
+      "तारीख से पंजीकरण को प्रमाणित करना होता है\n",
+      "इस विशेष प्रस्ताव खंड के उप खंड  सिक्स  के खंड  ए  के अनुसार\n",
+      "चलिए फिर से संक्षेप में\n",
+      " ऑलट्रेशन ऑफ मेमोरेंडम के महत्व के बारे में चर्चा करते हैं\n",
+      " क्योंकि ये इस मॉड्यूल के अध्ययन का एक बहुत महत्वपूर्ण हिस्सा है\n",
+      "पहला महत्व यह है\n",
+      "कि यह एक बहुत ही आवश्यक दस्तावेज है\n",
+      "एक कंपनी के निगमन के लिए\n",
+      "दूसरा यह कंपनी के पंजीकृत कार्यालय को निर्दिष्ट करते हुए\n",
+      "रजिस्ट्रार और अदालत के अधिकार क्षेत्र को निर्धारित करता है\n",
+      "तीसरा यह कंपनी के अधिकारों में उद्देश्यों को\n",
+      "जनता की जानकारी के लिए दर्ज करता है\n",
+      "अगला यह कंपनी को केवल उन कृत्यों को करने के लिए\n",
+      "बाध्य करता है जो कंपनी के ऑब्जेक्ट क्लॉज में शामिल हैं\n",
+      "यह कंपनी की अधिकृत कैपिटल\n",
+      "और उसके विभाजन को निश्चित राशि के शेयरों में निर्दिष्ट करता है\n",
+      "पर प्रकाश डालता है\n",
+      "यह कंपनी के सदस्यों के लायबिलिटी\n",
+      "अंत में संघ के नियमों को\n",
+      "यह एक कंपनी के भी नियंत्रित करता है\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "wb_obj = openpyxl.load_workbook(\"charmap_v2_new.xlsx\") \n",
+    "sheet_obj = wb_obj.active \n",
+    "\n",
+    "#data = re.sub('[A-Z]*', '',data)\n",
+    "#print(data)\n",
+    "data = data.replace('?','')\n",
+    "data = data.replace('  ',' ')\n",
+    "data = data.replace(';','')\n",
+    "data = data.replace(')','')\n",
+    "data = data.replace('(','')\n",
+    "data = data.replace('!','')\n",
+    "data = data.replace(' – ',' ')\n",
+    "data = data.replace('-',' ')\n",
+    "data = data.replace('।','')\n",
+    "data = data.replace('&','')\n",
+    "data = data.replace('’','')\n",
+    "data = data.replace('‘','')\n",
+    "data = data.replace(':','')\n",
+    "data = data.replace(',','')\n",
+    "data = data.replace('/','')\n",
+    "data = data.replace(',','')\n",
+    "data = data.replace('.','')\n",
+    "data = data.replace('|','')\n",
+    "m_row = sheet_obj.max_row \n",
+    "line = data\n",
+    "\n",
+    "for i in range(1,m_row+1):\n",
+    "    num = sheet_obj.cell(row = i, column = 1).value \n",
+    "    word = sheet_obj.cell(row = i, column = 2).value\n",
+    "    #print(num)\n",
+    "    #print(word)\n",
+    "    line = line.replace(str(num), word)\n",
+    "#print(line)\n",
+    "#' '.join(line.split())\n",
+    "print(line) \n",
+    "file1 = open(\"recent_deliverables_dec2020/Corporate_Law/Hindi/ankita objects 02_Hindi.txt\",\"w+\",encoding='utf-8') \n",
+    "file1.write(line)\n",
+    "file1.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

charmap/Text_Cleaning.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[2]:
+
+
+############################################################
+#Author : Bhagyashree
+#Date : 1st Sept, 2020
+#Purpose : Text Cleaning
+#Input : Text file after timestamp removal
+#Output : Text file after cleaning data
+############################################################
+
+
+# In[3]:
+
+
+import nltk
+import numpy
+import xlrd
+import openpyxl 
+import re
+import sys
+
+# In[21]:
+
+#file1 = open("recent_deliverables_dec2020/Corporate_Law/Hindi/ankita objects 02_Hindi_new.txt","r+",encoding='utf-8') 
+file1 = open(sys.argv[1],"r+",encoding='utf-8') 
+data = file1.read()
+#print(data)
+file1.close()
+
+
+# In[22]:
+
+wb_obj = openpyxl.load_workbook(sys.argv[2]) 
+sheet_obj = wb_obj.active 
+
+#data = re.sub('[A-Z]*', '',data)
+#print(data)
+data = data.replace('?','')
+data = data.replace('  ',' ')
+data = data.replace(';','')
+data = data.replace(')','')
+data = data.replace('(','')
+data = data.replace('!','')
+data = data.replace(' – ',' ')
+data = data.replace('-',' ')
+data = data.replace('।','')
+data = data.replace('&','')
+data = data.replace('’','')
+data = data.replace('‘','')
+data = data.replace(':','')
+data = data.replace(',','')
+data = data.replace('/','')
+data = data.replace(',','')
+data = data.replace('.','')
+data = data.replace('|','')
+m_row = sheet_obj.max_row 
+line = data
+
+for i in range(1,m_row+1):
+    num = sheet_obj.cell(row = i, column = 1).value 
+    word = sheet_obj.cell(row = i, column = 2).value
+    #print(num)
+    #print(word)
+    line = line.replace(str(num), word)
+#print(line)
+#' '.join(line.split())
+#print(line) 
+file1 = open(sys.argv[3],"w+",encoding='utf-8') 
+#file1 = open("recent_deliverables_dec2020/Corporate_Law/Hindi/ankita objects 02_Hindi.txt","w+",encoding='utf-8') 
+file1.write(line)
+file1.close()
+

charmap/charmap_Bengali.txt

@@ -0,0 +1,62 @@
+0	জিরো
+1	ওয়ান
+2	টু
+3	থ্রী
+4	ফোর
+5	ফাইভ
+6	সিক্স
+7	সেবন
+8	এইট
+9	নাইন
+A	এ
+a	এ
+B	বী
+b	বী
+C	সী
+c	সী
+D	ডি
+d	ডি
+E	ই
+e	ই
+F	এফ
+f	এফ
+G	জি
+g	জি
+H	এছ
+h	এছ
+I	আই
+i	আই
+J	জে
+j	জে
+K	কে
+k	কে
+L	এল
+l	এল
+M	এম
+m	এম
+N	এন
+n	এন
+O	ও
+o	ও
+P	পি
+p	পি
+Q	ক্যু
+q	ক্যু
+R	আর
+r	আর
+S	এস
+s	এস
+T	টি
+t	টি
+U	ইউ
+u	ইউ
+V	ভি
+v	ভি
+W	ডাবলু
+w	ডাবলু
+X	এক্স
+x	এক্স
+Y	উহাই
+y	উহাই
+Z	জেডঃ
+z	জেডঃ

charmap/charmap_Hindi.txt

@@ -0,0 +1,81 @@
+0	ज़ीरो
+1	वन
+2	टू
+3	थ्री
+4	फोर
+5	फाइव
+6	सिक्स
+7	सेवेन
+8	ऐइट
+9	नाइन
+०	ज़ीरो
+१	वन
+२	टू
+३	थ्री
+४	फोर
+५	फाइव
+६	सिक्स
+७	सेवेन
+८	ऐइट
+९	नाइन
+A	ए
+a	ए
+B	बी
+b	बी
+C	सी
+c	सी
+D	डी
+d	डी
+E	इ
+e	इ
+F	एफ
+f	एफ
+G	जी
+g	जी
+H	एच
+h	एच
+I	आई
+i	आई
+J	जे
+j	जे
+K	के
+k	के
+L	एल
+l	एल
+M	एम
+m	एम
+N	एन
+n	एन
+O	ओ
+o	ओ
+P	पी
+p	पी
+Q	क्यू
+q	क्यू
+R	आर
+r	आर
+S	एस
+s	एस
+T	टी
+t	टी
+U	यू
+u	यू
+V	वी
+v	वी
+W	डबलु
+w	डबलु
+X	एक्स
+x	एक्स
+Y	व्हाई
+y	व्हाई
+Z	ज़ेड
+z	ज़ेड
+α	अल्फा
+φ	फ़ाई
++	प्लस
+=	इक्वल
+λ	लैम्ब्डा
+∅	नॉट
+ϕ	फ़ाई
+𝝅	पाई
+⇒	इम्प्लइज

charmap/charmap_Malayalam.txt

@@ -0,0 +1,81 @@
+0	സീറോ
+1	വൺ
+2	ടു
+3	ത്രീ
+4	ഫോർ
+5	ഫൈവ്
+6	സിക്സ്
+7	സെവൻ
+8	എയ്റ്റ്
+9	നൈൻ
+0	സീറോ
+1	വൺ
+2	ടു
+3	ത്രീ
+4	ഫോർ
+5	ഫൈവ്
+6	സിക്സ്
+7	സെവൻ
+8	എയ്റ്റ്
+9	നൈൻ
+A	എ
+a	എ
+B	ബി
+b	ബി
+C	സി
+c	സി
+D	ഡി
+d	ഡി
+E	ഇ
+e	ഇ
+F	എഫ്
+f	എഫ്
+G	ജി
+g	ജി
+H	എഛ്
+h	എഛ്
+I	ഐ
+i	ഐ
+J	ജെ
+j	ജെ
+K	കെ
+k	കെ
+L	എൽ
+l	എൽ
+M	എം
+m	എം
+N	എൻ
+n	എൻ
+O	ഒ
+o	ഒ
+P	പി
+p	പി
+Q	ക്യു
+q	ക്യു
+R	ആർ
+r	ആർ
+S	എസ്
+s	എസ്
+T	ടി
+t	ടി
+U	യു
+u	യു
+V	വി
+v	വി
+W	ഡബ്ല്യൂ
+w	ഡബ്ല്യൂ
+X	എക്സ്
+x	എക്സ്
+Y	വൈ
+y	വൈ
+Z	സെഡ്
+z	സെഡ്
+α	ആൽഫ
+φ	ഫി
++	പ്ലസ്
+=	ഈക്വൽ
+λ	ലാംബ്ടാ
+∅	നോട്ട്
+ϕ	സൈ
+𝝅	പൈ
+⇒	ഇമ്പ്ലെയ്സ്

charmap/charmap_Marathi.txt

@@ -0,0 +1,81 @@
+0	ज़ीरो
+1	वन
+2	टू
+3	थ्री
+4	फोर
+5	फाइव
+6	सिक्स
+7	सेवेन
+8	ऐइट
+9	नाइन
+०	ज़ीरो
+१	वन
+२	टू
+३	थ्री
+४	फोर
+५	फाइव
+६	सिक्स
+७	सेवेन
+८	ऐइट
+९	नाइन
+A	ए
+a	ए
+B	बी
+b	बी
+C	सी
+c	सी
+D	डी
+d	डी
+E	इ
+e	इ
+F	एफ
+f	एफ
+G	जी
+g	जी
+H	एच
+h	एच
+I	आई
+i	आई
+J	जे
+j	जे
+K	के
+k	के
+L	एल
+l	एल
+M	एम
+m	एम
+N	एन
+n	एन
+O	ओ
+o	ओ
+P	पी
+p	पी
+Q	क्यू
+q	क्यू
+R	आर
+r	आर
+S	एस
+s	एस
+T	टी
+t	टी
+U	यू
+u	यू
+V	वी
+v	वी
+W	डबलु
+w	डबलु
+X	एक्स
+x	एक्स
+Y	व्हाई
+y	व्हाई
+Z	ज़ेड
+z	ज़ेड
+α	अल्फा
+φ	फ़ाई
++	प्लस
+=	इक्वल
+λ	लैम्ब्डा
+∅	नॉट
+ϕ	फ़ाई
+𝝅	पाई
+⇒	इम्प्लइज

charmap/charmap_Tamil.disabled

@@ -0,0 +1,76 @@
+0	ஸிரோ
+1	ஒன்னு
+2	டூ
+3	த்ரீ
+4	போர்
+5	பைவ்
+6	சீஸ்
+7	செவென்
+8	எயிட்
+9	நயன்
+A	எ
+a	எ
+B	பி
+b	பி
+C	சி
+c	சி
+D	டி
+d	டி
+E	இ
+e	இ
+F	எப்
+f	எப்
+G	ஜி
+g	ஜி
+H	ஹ்
+h	ஹ்
+I	ஐ
+i	ஐ
+J	ஜே
+j	ஜே
+K	கே
+k	கே
+L	ல்
+l	ல்
+M	ம்
+m	ம்
+N	ன்
+n	ன்
+O	ஓ
+o	ஓ
+P	பி
+p	பி
+Q	கியூ
+q	கியூ
+R	ர்
+r	ர்
+S	ஸ்
+s	ஸ்
+T	டீ
+t	டீ
+U	யூ
+u	யூ
+V	வி
+v	வி
+W	டௌபிள்யூ
+w	டௌபிள்யூ
+X	எஸ்
+x	எஸ்
+Y	யை
+y	யை
+Z	செட்
+z	செட்
+α	ஆல்பா
+φ	பிய்
++	பிளஸ்
+=	ஏகுவாள்
+λ	லாம்டா
+∅	நோட்
+ϕ	பிய்
+𝝅	பை
+⇒	இம்ப்ளிஸ்
+.	பாயிண்ட்
+%	பெர்ஸண்டாஜ்
+°C	டிகிரிசெல்சியஸ்
+θ	தீட்டா
+*	இண்டூ

charmap/charmap_Telugu.txt

@@ -0,0 +1,81 @@
+0	జీరొ
+1	వన్
+2	టు
+3	త్రీ
+4	ఫోర్
+5	ఫైవ్
+6	సిక్స్
+7	సెవెన్
+8	ఎఇట్
+9	నైన్
+०	జీరొ
+१	వన్
+२	టు
+३	త్రీ
+४	ఫోర్
+५	ఫైవ్
+६	సిక్స్
+७	సెవెన్
+८	ఎఇట్
+९	నైన్
+A	ఎ
+a	ఎ
+B	బి
+b	బి
+C	సి
+c	సి
+D	డి
+d	డి
+E	ఇ
+e	ఇ
+F	ఎఫ్
+f	ఎఫ్
+G	జి
+g	జి
+H	హెచ్
+h	హెచ్
+I	ఐ
+i	ఐ
+J	జె
+j	జె
+K	కె
+k	కె
+L	ఎల్
+l	ఎల్
+M	ఎమ్
+m	ఎమ్
+N	ఎన్
+n	ఎన్
+O	ఒ
+o	ఒ
+P	పి
+p	పి
+Q	క్యు
+q	క్యు
+R	ఆర్
+r	ఆర్
+S	ఎస్
+s	ఎస్
+T	టి
+t	టి
+U	యు
+u	యు
+V	వి
+v	వి
+W	డబ్లు
+w	డబ్లు
+X	ఎక్స్
+x	ఎక్స్
+Y	వై
+y	వై
+Z	జెడ్
+z	జెడ్
+α	ఆల్ఫ
+φ	ఫై
++	ప్లస్
+=	ఈక్వల్
+λ	లామ్బ్డ
+∅	నల్
+ϕ	ఫై
+𝝅	పై
+⇒	ఇమ్ప్లైస్

dogri_latest/female/model/config.yaml

@@ -0,0 +1,320 @@
+accum_grad: 8
+adapter: lora
+adapter_conf: {}
+allow_multi_rates: false
+allow_variable_data_keys: false
+batch_bins: 3000000
+batch_size: 20
+batch_type: numel
+best_model_criterion:
+- - valid
+  - loss
+  - min
+- - train
+  - loss
+  - min
+bpemodel: null
+category_sample_size: 10
+chunk_default_fs: null
+chunk_discard_short_samples: true
+chunk_excluded_key_prefixes: []
+chunk_length: 500
+chunk_max_abs_length: null
+chunk_shift_ratio: 0.5
+cleaner: null
+collect_stats: false
+config: conf/tuning/train_fastspeech2.yaml
+create_graph_in_tensorboard: false
+cudnn_benchmark: false
+cudnn_deterministic: true
+cudnn_enabled: true
+deepspeed_config: null
+detect_anomaly: false
+dist_backend: nccl
+dist_init_method: env://
+dist_launcher: null
+dist_master_addr: localhost
+dist_master_port: 33333
+dist_rank: 0
+dist_world_size: 2
+distributed: true
+drop_last_iter: false
+dry_run: false
+early_stopping_criterion:
+- valid
+- loss
+- min
+energy_extract: energy
+energy_extract_conf:
+  fs: 48000
+  hop_length: 1024
+  n_fft: 8192
+  reduction_factor: 1
+  win_length: 4096
+energy_normalize: global_mvn
+energy_normalize_conf:
+  stats_file: /home/speech/Suji/FS2/Fastspeech2_HS/Models_ph3/Dogri_fem_mono/energy_stats.npz
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+feats_extract: fbank
+feats_extract_conf:
+  fmax: 24000
+  fmin: 0
+  fs: 48000
+  hop_length: 1024
+  n_fft: 8192
+  n_mels: 160
+  win_length: 4096
+fold_length:
+- 150
+- 819200
+freeze_param: []
+g2p: null
+grad_clip: 1.0
+grad_clip_type: 2.0
+grad_noise: false
+ignore_init_mismatch: false
+init_param: []
+iterator_type: sequence
+keep_nbest_models: 5
+local_rank: 0
+log_interval: null
+log_level: INFO
+max_cache_fd: 32
+max_cache_size: 0.0
+max_epoch: 1000
+model_conf: {}
+multi_task_dataset: false
+multiple_iterator: false
+multiprocessing_distributed: true
+nbest_averaging_interval: 0
+ngpu: 1
+no_forward_run: false
+non_linguistic_symbols: null
+normalize: global_mvn
+normalize_conf:
+  stats_file: /home/speech/Suji/FS2/Fastspeech2_HS/Models_ph3/Dogri_fem_mono/feats_stats.npz
+num_att_plot: 3
+num_cache_chunks: 1024
+num_iters_per_epoch: 800
+num_workers: 1
+odim: null
+optim: adam
+optim_conf:
+  lr: 1.0
+output_dir: exp/tts_train_fastspeech2_raw_char_None
+patience: null
+pitch_extract: dio
+pitch_extract_conf:
+  f0max: 400
+  f0min: 80
+  fs: 48000
+  hop_length: 1024
+  n_fft: 8192
+  reduction_factor: 1
+pitch_normalize: global_mvn
+pitch_normalize_conf:
+  stats_file: /home/speech/Suji/FS2/Fastspeech2_HS/Models_ph3/Dogri_fem_mono/pitch_stats.npz
+pretrain_path: null
+print_config: false
+required:
+- output_dir
+- token_list
+resume: true
+save_strategy: all
+scheduler: noamlr
+scheduler_conf:
+  model_size: 384
+  warmup_steps: 4000
+seed: 0
+sharded_ddp: false
+shuffle_within_batch: false
+sort_batch: descending
+sort_in_batch: descending
+token_list:
+- <blank>
+- <unk>
+- <space>
+- $
+- ','
+- .
+- M
+- q
+- H
+- k
+- "\u0916"
+- g
+- "\u0918"
+- "\u0919"
+- c
+- C
+- j
+- J
+- "\u091E"
+- "\u091F"
+- "\u0920"
+- "\u0921"
+- "\u0922"
+- "\u0923"
+- t
+- "\u0925"
+- d
+- "\u0927"
+- n
+- "\u0929"
+- p
+- P
+- b
+- B
+- m
+- y
+- r
+- "\u0931"
+- l
+- "\u0D33"
+- Z
+- w
+- "\u0936"
+- "\u0937"
+- s
+- h
+- Y
+- "\u093D"
+- "\u0915"
+- K
+- G
+- z
+- D
+- T
+- f
+- "\u0960"
+- "\u0D7A"
+- N
+- "\u0D7C"
+- "\u0D7D"
+- "\u0D7E"
+- a
+- A
+- i
+- I
+- u
+- U
+- R
+- "\u090D"
+- e
+- E
+- "\u0910"
+- "\u0911"
+- o
+- O
+- "\u0914"
+- "\u0B89"
+- <sos/eos>
+token_type: char
+train_data_path_and_name_and_type:
+- - dump/raw/tr_no_dev/text
+  - text
+  - text
+- - duration_info/tr_no_dev/durations
+  - durations
+  - text_int
+- - dump/raw/tr_no_dev/wav.scp
+  - speech
+  - sound
+- - exp/tts_stats_raw_char_None/train/collect_feats/pitch.scp
+  - pitch
+  - npy
+- - exp/tts_stats_raw_char_None/train/collect_feats/energy.scp
+  - energy
+  - npy
+train_dtype: float32
+train_shape_file:
+- exp/tts_stats_raw_char_None/train/text_shape.char
+- exp/tts_stats_raw_char_None/train/speech_shape
+tts: fastspeech2
+tts_conf:
+  adim: 384
+  aheads: 2
+  decoder_normalize_before: true
+  dlayers: 4
+  dunits: 1536
+  duration_predictor_chans: 256
+  duration_predictor_kernel_size: 3
+  duration_predictor_layers: 2
+  elayers: 4
+  encoder_normalize_before: true
+  energy_embed_dropout: 0.0
+  energy_embed_kernel_size: 1
+  energy_predictor_chans: 256
+  energy_predictor_dropout: 0.5
+  energy_predictor_kernel_size: 3
+  energy_predictor_layers: 2
+  eunits: 1536
+  init_dec_alpha: 1.0
+  init_enc_alpha: 1.0
+  init_type: xavier_uniform
+  pitch_embed_dropout: 0.0
+  pitch_embed_kernel_size: 1
+  pitch_predictor_chans: 256
+  pitch_predictor_dropout: 0.5
+  pitch_predictor_kernel_size: 5
+  pitch_predictor_layers: 5
+  positionwise_conv_kernel_size: 3
+  positionwise_layer_type: conv1d
+  postnet_chans: 256
+  postnet_filts: 5
+  postnet_layers: 5
+  reduction_factor: 1
+  stop_gradient_from_energy_predictor: false
+  stop_gradient_from_pitch_predictor: true
+  transformer_dec_attn_dropout_rate: 0.2
+  transformer_dec_dropout_rate: 0.2
+  transformer_dec_positional_dropout_rate: 0.2
+  transformer_enc_attn_dropout_rate: 0.2
+  transformer_enc_dropout_rate: 0.2
+  transformer_enc_positional_dropout_rate: 0.2
+  use_masking: true
+  use_scaled_pos_enc: true
+unused_parameters: false
+use_adapter: false
+use_amp: false
+use_deepspeed: false
+use_matplotlib: true
+use_preprocessor: true
+use_tensorboard: true
+use_tf32: false
+use_wandb: false
+val_scheduler_criterion:
+- valid
+- loss
+valid_batch_bins: null
+valid_batch_size: null
+valid_batch_type: null
+valid_data_path_and_name_and_type:
+- - dump/raw/dev/text
+  - text
+  - text
+- - duration_info/dev/durations
+  - durations
+  - text_int
+- - dump/raw/dev/wav.scp
+  - speech
+  - sound
+- - exp/tts_stats_raw_char_None/valid/collect_feats/pitch.scp
+  - pitch
+  - npy
+- - exp/tts_stats_raw_char_None/valid/collect_feats/energy.scp
+  - energy
+  - npy
+valid_iterator_type: null
+valid_max_cache_size: null
+valid_shape_file:
+- exp/tts_stats_raw_char_None/valid/text_shape.char
+- exp/tts_stats_raw_char_None/valid/speech_shape
+version: '202412'
+wandb_entity: null
+wandb_id: null
+wandb_model_log_interval: -1
+wandb_name: null
+wandb_project: null
+write_collected_feats: false

dogri_latest/female/model/energy_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb130c5668e5ed45e934c17a1538a8756c5eb9c68815ba5d32533e45852eb3a
+size 770

dogri_latest/female/model/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19d99c343e9d668bd1823dc2ca76ded554b799251ff82714836b467044f1f6b
+size 2042