Added IAT and TTS SDK for app

.gitignore

@@ -0,0 +1,179 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python
+
+config.yaml
+

.vscode/settings.json

@@ -0,0 +1,4 @@
+{
+    "python.analysis.autoImportCompletions": true,
+    "python.analysis.typeCheckingMode": "basic"
+}

iat.py

@@ -0,0 +1,106 @@
+from urllib.parse import urlparse, urlencode
+from wsgiref.handlers import format_date_time
+from datetime import datetime
+import hmac
+import hashlib
+import base64
+import numpy as np
+import json
+import websockets.client
+from websockets.exceptions import ConnectionClosedError
+import time
+
+STATUS_FIRST_FRAME = 0
+STATUS_CONTINUE_FRAME = 1
+STATUS_LAST_FRAME = 2
+
+'''
+XFYun's IAT Client, which is used to convert speech to text.
+'''
+class IATClient:
+    def __init__(
+        self,
+        app_id: str,
+        api_key: str,
+        api_secret: str,
+        endpoint="wss://ws-api.xfyun.cn/v2/iat",
+    ) -> None:
+        self.app_id = app_id
+        self.api_key = api_key
+        self.api_secret = api_secret
+        self.endpoint = endpoint
+        self.common_args = {"app_id": self.app_id}
+        self.business_args = {
+            "domain": "iat",
+            "language": "zh_cn",
+            "accent": "mandarin",
+            "vinfo": 1,
+            "vad_eos": 10000,
+        }
+
+    # To convert ndarray audio data to PCM-style bytes
+    # Gradio Audio Module returns a tuple of (sampling_rate, np.ndarray)
+    # And the np.ndarray is the audio data, which is range from -32768 to 32767 matching PCM range.
+    def encode_pcm(self, source: np.ndarray):
+        return source.astype(np.int16).tobytes()
+
+    def create_url(self):
+        parse_result = urlparse(self.endpoint)
+        host = parse_result.hostname
+        # RFC1123 Timestamp
+        date = format_date_time(time.mktime(datetime.now().timetuple()))
+        path = parse_result.path
+
+        sign_raw_str = f"host: {host}\ndate: {date}\nGET {path} HTTP/1.1"
+        sign_sha = hmac.new(
+            self.api_secret.encode("utf-8"),
+            sign_raw_str.encode("utf-8"),
+            digestmod=hashlib.sha256,
+        ).digest()
+        auth_origin = 'api_key="%s", algorithm="%s", headers="%s", signature="%s"' % (
+            self.api_key,
+            "hmac-sha256",
+            "host date request-line",
+            sign_sha,
+        )
+        auth = base64.b64encode(auth_origin.encode("utf-8")).decode("utf-8")
+        params = {
+            "authorization": auth,
+            "date": date,
+            "host": host,
+        }
+        url = f"{self.endpoint}?{urlencode(params)}"
+        return url
+
+    def prepare_data(self, audio: bytes, chunk_size=1280, sampling_rate=16000):
+        status = STATUS_FIRST_FRAME
+        for i in range(0, len(audio), chunk_size):
+            chunk = audio[i : i + chunk_size]
+            if i + chunk_size >= len(audio):
+                status = STATUS_LAST_FRAME
+            data = {
+                "status": status,
+                "format": f"audio/L16;rate={sampling_rate}",
+                "audio": base64.b64encode(chunk).decode("utf-8"),
+                "encoding": "raw",
+            }
+            payload = {"data": data}
+            if status == STATUS_FIRST_FRAME:
+                payload["common"] = self.common_args
+                payload["business"] = self.business_args
+            yield payload
+            status = STATUS_CONTINUE_FRAME
+
+    async def dictate(self, audio: tuple[int, np.ndarray], interval=0.4):
+        url = self.create_url()
+        sampling_rate, source = audio
+        pcm = self.encode_pcm(source)
+        async with websockets.client.connect(url) as ws:
+            for payload in self.prepare_data(pcm, sampling_rate=sampling_rate):
+                await ws.send(json.dumps(payload))
+                time.sleep(interval)
+            try:
+                async for message in ws:
+                    yield message
+            except ConnectionClosedError as e:
+                print(f"Connection closed: {e.code} {e.reason}")

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+jupyter
+requests
+websocket-client
+zhipuai
+loguru
+numpy

tts.py

@@ -0,0 +1,98 @@
+from urllib.parse import urlparse, urlencode
+from wsgiref.handlers import format_date_time
+from datetime import datetime
+import hmac
+import hashlib
+import base64
+import numpy as np
+import json
+import websockets.client
+from websockets.exceptions import ConnectionClosedError
+import time
+
+STATUS_FIRST_FRAME = 0
+STATUS_CONTINUE_FRAME = 1
+STATUS_LAST_FRAME = 2
+
+
+class TTSClient:
+
+    def __init__(
+        self,
+        app_id: str,
+        api_key: str,
+        api_secret: str,
+        endpoint="wss://ws-api.xfyun.cn/v2/tts",
+    ) -> None:
+        self.app_id = app_id
+        self.api_key = api_key
+        self.api_secret = api_secret
+        self.endpoint = endpoint
+        self.common_args = {"app_id": self.app_id}
+        self.business_args = {
+            "aue": "raw",
+            "auf": "audio/L16;rate=16000",
+            "vcn": "xiaoyan",
+            "tte": "utf8",
+        }
+
+    def prepare_data(self, text: str):
+        return {
+            "common": self.common_args,
+            "business": self.business_args,
+            "data": {
+                "status": 2,
+                "text": str(base64.b64encode(text.encode("utf-8")), "UTF8"),
+            },
+        }
+
+    def create_url(self):
+        parse_result = urlparse(self.endpoint)
+        host = parse_result.hostname
+        # RFC1123 Timestamp
+        date = format_date_time(time.mktime(datetime.now().timetuple()))
+        path = parse_result.path
+
+        sign_raw_str = f"host: {host}\ndate: {date}\nGET {path} HTTP/1.1"
+        sign_sha = hmac.new(
+            self.api_secret.encode("utf-8"),
+            sign_raw_str.encode("utf-8"),
+            digestmod=hashlib.sha256,
+        ).digest()
+        auth_origin = 'api_key="%s", algorithm="%s", headers="%s", signature="%s"' % (
+            self.api_key,
+            "hmac-sha256",
+            "host date request-line",
+            sign_sha,
+        )
+        auth = base64.b64encode(auth_origin.encode("utf-8")).decode("utf-8")
+        params = {
+            "authorization": auth,
+            "date": date,
+            "host": host,
+        }
+        url = f"{self.endpoint}?{urlencode(params)}"
+        return url
+
+    def parse_result(self, result: bytes) -> np.ndarray:
+        return np.frombuffer(result, dtype=np.int16)
+
+    async def generate(self, text: str):
+        url = self.create_url()
+        data = self.prepare_data(text)
+        result = bytearray()
+        async with websockets.client.connect(url) as ws:
+            await ws.send(json.dumps(data))
+            while True:
+                try:
+                    message = await ws.recv()
+                    message = json.loads(message)
+                    audio = message["data"]["audio"]
+                    audio = base64.b64decode(audio)
+                    status = message["data"]["status"]
+                    result += audio
+                    if status == STATUS_LAST_FRAME:
+                        break
+                except ConnectionClosedError:
+                    break
+        return self.parse_result(bytes(result))