jimmyvu commited on Feb 1

Commit

e846c6e

1 Parent(s): a164a9f

Update with fresh new models

Browse files

Files changed (45) hide show

README.md +0 -130
banmai.onnx.json +0 -1
calmwoman3688.onnx +0 -3
calmwoman3688.onnx.json +0 -1
chieuthanh.onnx.json +0 -1
deepman3909.onnx.json +0 -1
chieuthanh.onnx → deepvoice-man-south.onnx +1 -1
indo.onnx.json → deepvoice-man-south.onnx.json +1 -1
duyorynx3175.onnx.json +0 -1
duyoryx3175.onnx +0 -3
banmai.onnx → friendly-man-persuasive.onnx +1 -1
mattheo.onnx.json → friendly-man-persuasive.onnx.json +1 -1
indo.onnx +0 -3
lacphi.onnx +0 -3
lacphi.onnx.json +0 -1
deepman3909.onnx → loud-fast-man-southern.onnx +1 -1
mattheo1.onnx.json → loud-fast-man-southern.onnx.json +1 -1
maiphuong.onnx +0 -3
maiphuong.onnx.json +0 -1
manhdung.onnx +0 -3
manhdung.onnx.json +0 -1
mattheo.onnx +0 -3
mattheo1.onnx +0 -3
minhquang.onnx +0 -3
minhquang.onnx.json +0 -1
mytam2.onnx +0 -3
mytam2.onnx.json +0 -1
mytam2794.onnx +0 -3
mytam2794.onnx.json +0 -1
ngochuyen.onnx +0 -3
ngochuyen.onnx.json +0 -1
ngocngan3701.onnx +0 -3
ngocngan3701.onnx.json +0 -1
phuongtrang.onnx +0 -3
phuongtrang.onnx.json +0 -1
taian1.onnx +0 -3
taian1.onnx.json +0 -1
thanhphuong2.onnx +0 -3
thanhphuong2.onnx.json +0 -1
thientam.onnx +0 -3
thientam.onnx.json +0 -1
tranthanh3870.onnx +0 -3
tranthanh3870.onnx.json +0 -1
vietthao3886.onnx +0 -3
vietthao3886.onnx.json +0 -1

README.md DELETED Viewed

@@ -1,130 +0,0 @@
-# viPiper Models
-This directory contains Vietnamese Text-to-Speech (TTS) model files for the viPiper project, powered by Piper TTS and ONNX Runtime.
-## What is this?
-These are pre-trained Vietnamese TTS models that convert Vietnamese text to natural-sounding speech. The models are based on [Piper TTS](https://github.com/rhasspy/piper), optimized for fast, local inference.
-## File Structure
-Each model requires **two files**:
-- `{model_name}.onnx` - The ONNX neural network model (~60-80 MB)
-- `{model_name}.onnx.json` - Configuration file containing:
-  - `phoneme_id_map`: Phoneme-to-ID mapping
-  - `sample_rate`: Audio sample rate (typically 22050 Hz)
-  - `num_speakers`: Number of speakers in the model
-  - `speaker_id_map`: Speaker names and IDs (for multi-speaker models)
-  - Voice and audio settings
-## Available Models
-The following Vietnamese TTS models are available:
-- **banmai** - Female voice
-- **calmwoman3688** - Calm female voice
-- **chieuthanh** - Male voice
-- **deepman3909** - Deep male voice
-- **duyorynx3175** - Male voice
-- **indo** - Indonesian voice (supports English)
-- **lacphi** - Male voice
-- **maiphuong** - Female voice
-- **manhdung** - Male voice
-- **mattheo** / **mattheo1** - Male voice
-- **minhquang** - Male voice
-- **mytam2** / **mytam2794** - Female voice (My Tam style)
-- **ngochuyen** - Female voice
-- **ngocngan3701** - Female voice
-- **phuongtrang** - Female voice
-## Usage
-### With viPiper Python Package
-```python
-from viPiper import TTSEngine
-# Initialize engine
-engine = TTSEngine(models_dir="./models")
-# Synthesize speech
-audio = engine.synthesize(
-    text="Xin chao, day la ban demo chuyen doi van ban thanh giong noi.",
-    model_name="banmai",
-    speaker_id=0,
-    speed=1.0
-)
-# Save to file
-audio.to_wav("output.wav")
-```
-### With Gradio Demo
-```bash
-# Install viPiper
-pip install -e .
-# Launch the demo interface
-viPiper-demo --models-dir ./models
-# Or
-python -m viPiper.demo --models-dir ./models
-```
-The demo will open at `http://127.0.0.1:7860` with an interactive web interface.
-### With REST API
-```bash
-# Start the API server
-viPiper-api --models-dir ./models
-# Or
-python -m viPiper.api --models-dir ./models
-```
-The API will be available at `http://127.0.0.1:8000`. See the OpenAPI docs at `http://127.0.0.1:8000/docs`.
-**Example API call:**
-```python
-import requests
-response = requests.post(
-    "http://127.0.0.1:8000/synthesize",
-    json={
-        "text": "Xin chao, day la viPiper",
-        "model_name": "banmai",
-        "speaker_id": 0,
-        "speed": 1.0
-    }
-)
-# Save the audio response
-with open("output.wav", "wb") as f:
-    f.write(response.content)
-```
-## Features
-- **High Quality**: Natural-sounding Vietnamese speech
-- **Fast Inference**: ~5x real-time speed
-- **Multi-Speaker**: Some models support multiple voices
-- **Speed Control**: Adjustable speech speed (0.5x - 2.0x)
-- **Open Format**: Standard ONNX format for broad compatibility
-- **OpenAI-Compatible API**: Easy integration with existing tools
-## Requirements
-- Python 3.9+
-- onnxruntime>=1.16.0
-- numpy>=1.24.0
-- piper-phonemize~=1.1.0 (for phoneme processing)
-## License
-These models are provided for use with the viPiper project. Please refer to the main project repository for licensing information.
-## Model Training
-These models were fine-tuned from Piper TTS base checkpoints using custom Vietnamese datasets (~1,000 audio samples, ~2,000 epochs). See the project documentation for training details and dataset downloads.

banmai.onnx.json DELETED Viewed

@@ -1 +0,0 @@

- {"audio": {"sample_rate": 22050},"espeak": {"voice": "vi"},"phoneme_type": "espeak","num_symbols": 256,"num_speakers": 1,"inference": {"noise_scale": 0.667,"length_scale": 1.0,"noise_w": 0.8},"phoneme_id_map": {"_": [0],"^": [1],"$": [2]," ": [3],"!": [4],"'": [5],"(": [6],")": [7],",": [8],"-": [9],".": [10],":": [11],";": [12],"?": [13],"a": [14],"b": [15],"c": [16],"d": [17],"e": [18],"f": [19],"h": [20],"i": [21],"j": [22],"k": [23],"l": [24],"m": [25],"n": [26],"o": [27],"p": [28],"q": [29],"r": [30],"s": [31],"t": [32],"u": [33],"v": [34],"w": [35],"x": [36],"y": [37],"z": [38],"æ": [39],"ç": [40],"ð": [41],"ø": [42],"ħ": [43],"ŋ": [44],"œ": [45],"ǀ": [46],"ǁ": [47],"ǂ": [48],"ǃ": [49],"ɐ": [50],"ɑ": [51],"ɒ": [52],"ɓ": [53],"ɔ": [54],"ɕ": [55],"ɖ": [56],"ɗ": [57],"ɘ": [58],"ə": [59],"ɚ": [60],"ɛ": [61],"ɜ": [62],"ɞ": [63],"ɟ": [64],"ɠ": [65],"ɡ": [66],"ɢ": [67],"ɣ": [68],"ɤ": [69],"ɥ": [70],"ɦ": [71],"ɧ": [72],"ɨ": [73],"ɪ": [74],"ɫ": [75],"ɬ": [76],"ɭ": [77],"ɮ": [78],"ɯ": [79],"ɰ": [80],"ɱ": [81],"ɲ": [82],"ɳ": [83],"ɴ": [84],"ɵ": [85],"ɶ": [86],"ɸ": [87],"ɹ": [88],"ɺ": [89],"ɻ": [90],"ɽ": [91],"ɾ": [92],"ʀ": [93],"ʁ": [94],"ʂ": [95],"ʃ": [96],"ʄ": [97],"ʈ": [98],"ʉ": [99],"ʊ": [100],"ʋ": [101],"ʌ": [102],"ʍ": [103],"ʎ": [104],"ʏ": [105],"ʐ": [106],"ʑ": [107],"ʒ": [108],"ʔ": [109],"ʕ": [110],"ʘ": [111],"ʙ": [112],"ʛ": [113],"ʜ": [114],"ʝ": [115],"ʟ": [116],"ʡ": [117],"ʢ": [118],"ʲ": [119],"ˈ": [120],"ˌ": [121],"ː": [122],"ˑ": [123],"˞": [124],"β": [125],"θ": [126],"χ": [127],"ᵻ": [128],"ⱱ": [129],"0": [130],"1": [131],"2": [132],"3": [133],"4": [134],"5": [135],"6": [136],"7": [137],"8": [138],"9": [139],"̧": [140],"̃": [141],"̪": [142],"̯": [143],"̩": [144],"ʰ": [145],"ˤ": [146],"ε": [147],"↓": [148],"#": [149],"\"": [150],"↑": [151],"̺": [152],"̻": [153],"g": [154],"ʦ": [155],"X": [156],"̝": [157],"̊": [158],"ɝ": [159],"ʷ": [160],"̀": [161],"́": [162],"̂": [163],"̆": [164],"̇": [165],"̈": [166],"̉": [167],"̌": [168],"̣": [169],"̛": [170]},"speaker_id_map": {},"hop_length": 256,"piper_version": "1.3.0"}

calmwoman3688.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8db60d8afc50dc0921fd3a1b0b942813f44cc3744dbe2534617f2b8726096e7e
-size 63516050

calmwoman3688.onnx.json DELETED Viewed

@@ -1 +0,0 @@

chieuthanh.onnx.json DELETED Viewed

@@ -1 +0,0 @@

- {"audio": {"sample_rate": 22050},"espeak": {"voice": "vi-vn-x-south"},"phoneme_type": "espeak","num_symbols": 256,"num_speakers": 1,"inference": {"noise_scale": 0.667,"length_scale": 1.0,"noise_w": 0.8},"phoneme_id_map": {"_": [0],"^": [1],"$": [2]," ": [3],"!": [4],"'": [5],"(": [6],")": [7],",": [8],"-": [9],".": [10],":": [11],";": [12],"?": [13],"a": [14],"b": [15],"c": [16],"d": [17],"e": [18],"f": [19],"h": [20],"i": [21],"j": [22],"k": [23],"l": [24],"m": [25],"n": [26],"o": [27],"p": [28],"q": [29],"r": [30],"s": [31],"t": [32],"u": [33],"v": [34],"w": [35],"x": [36],"y": [37],"z": [38],"æ": [39],"ç": [40],"ð": [41],"ø": [42],"ħ": [43],"ŋ": [44],"œ": [45],"ǀ": [46],"ǁ": [47],"ǂ": [48],"ǃ": [49],"ɐ": [50],"ɑ": [51],"ɒ": [52],"ɓ": [53],"ɔ": [54],"ɕ": [55],"ɖ": [56],"ɗ": [57],"ɘ": [58],"ə": [59],"ɚ": [60],"ɛ": [61],"ɜ": [62],"ɞ": [63],"ɟ": [64],"ɠ": [65],"ɡ": [66],"ɢ": [67],"ɣ": [68],"ɤ": [69],"ɥ": [70],"ɦ": [71],"ɧ": [72],"ɨ": [73],"ɪ": [74],"ɫ": [75],"ɬ": [76],"ɭ": [77],"ɮ": [78],"ɯ": [79],"ɰ": [80],"ɱ": [81],"ɲ": [82],"ɳ": [83],"ɴ": [84],"ɵ": [85],"ɶ": [86],"ɸ": [87],"ɹ": [88],"ɺ": [89],"ɻ": [90],"ɽ": [91],"ɾ": [92],"ʀ": [93],"ʁ": [94],"ʂ": [95],"ʃ": [96],"ʄ": [97],"ʈ": [98],"ʉ": [99],"ʊ": [100],"ʋ": [101],"ʌ": [102],"ʍ": [103],"ʎ": [104],"ʏ": [105],"ʐ": [106],"ʑ": [107],"ʒ": [108],"ʔ": [109],"ʕ": [110],"ʘ": [111],"ʙ": [112],"ʛ": [113],"ʜ": [114],"ʝ": [115],"ʟ": [116],"ʡ": [117],"ʢ": [118],"ʲ": [119],"ˈ": [120],"ˌ": [121],"ː": [122],"ˑ": [123],"˞": [124],"β": [125],"θ": [126],"χ": [127],"ᵻ": [128],"ⱱ": [129],"0": [130],"1": [131],"2": [132],"3": [133],"4": [134],"5": [135],"6": [136],"7": [137],"8": [138],"9": [139],"̧": [140],"̃": [141],"̪": [142],"̯": [143],"̩": [144],"ʰ": [145],"ˤ": [146],"ε": [147],"↓": [148],"#": [149],"\"": [150],"↑": [151],"̺": [152],"̻": [153],"g": [154],"ʦ": [155],"X": [156],"̝": [157],"̊": [158],"ɝ": [159],"ʷ": [160],"̀": [161],"́": [162],"̂": [163],"̆": [164],"̇": [165],"̈": [166],"̉": [167],"̌": [168],"̣": [169],"̛": [170]},"speaker_id_map": {},"hop_length": 256,"piper_version": "1.3.0"}

deepman3909.onnx.json DELETED Viewed

@@ -1 +0,0 @@

chieuthanh.onnx → deepvoice-man-south.onnx RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b3059395e1d2f3d7499deaf3463615b5281c607465ea274d82ce84d93d61ac3
 size 63516050

 version https://git-lfs.github.com/spec/v1
+oid sha256:940a7e4f7a5be644ce3474e00d43d0e4c20b93244abc6073260e367c2708721f
 size 63516050

indo.onnx.json → deepvoice-man-south.onnx.json RENAMED Viewed

@@ -3,7 +3,7 @@
     "sample_rate": 22050
   },
   "espeak": {
-    "voice": "id"
   },
   "phoneme_type": "espeak",
   "num_symbols": 256,

     "sample_rate": 22050
   },
   "espeak": {
+    "voice": "vi"
   },
   "phoneme_type": "espeak",
   "num_symbols": 256,

duyorynx3175.onnx.json DELETED Viewed

@@ -1 +0,0 @@

duyoryx3175.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0d6f6b95eee7256f18115c09ad1cbdb69acddf87761549ec1a7decd19a4eba5c
-size 63516050

banmai.onnx → friendly-man-persuasive.onnx RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f599998f244511edd3df757febc0653ee94bfdbe673740f25c98c9b9b374984
 size 63516050

 version https://git-lfs.github.com/spec/v1
+oid sha256:ec6f653a2b7d93c71489ce375de30c3656ffb56180ad152830ca7219e05607c8
 size 63516050

mattheo.onnx.json → friendly-man-persuasive.onnx.json RENAMED Viewed

@@ -3,7 +3,7 @@
     "sample_rate": 22050
   },
   "espeak": {
-    "voice": "en"
   },
   "phoneme_type": "espeak",
   "num_symbols": 256,

     "sample_rate": 22050
   },
   "espeak": {
+    "voice": "vi"
   },
   "phoneme_type": "espeak",
   "num_symbols": 256,

indo.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:86c88725aacc46cb5b6e6400f52e75a6a10b8a7381513aac2e99de815402ef63
-size 63516050

lacphi.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c6e496c69c05f6043efd9967f0fb98d34b7cf94b0e698de43169253d34b318b2
-size 63516050

lacphi.onnx.json DELETED Viewed

@@ -1 +0,0 @@

deepman3909.onnx → loud-fast-man-southern.onnx RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb3a404e9927c87367d4175e8cad24ffc6d9959af29888c38682e5ec621056c
 size 63516050

 version https://git-lfs.github.com/spec/v1
+oid sha256:421f0ae43fb840cf5c43413ea1506c3294c8be6e31941635e70ac57f89600fe0
 size 63516050

mattheo1.onnx.json → loud-fast-man-southern.onnx.json RENAMED Viewed

@@ -3,7 +3,7 @@
     "sample_rate": 22050
   },
   "espeak": {
-    "voice": "en"
   },
   "phoneme_type": "espeak",
   "num_symbols": 256,

     "sample_rate": 22050
   },
   "espeak": {
+    "voice": "vi"
   },
   "phoneme_type": "espeak",
   "num_symbols": 256,

maiphuong.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3d8384d05a0569be1a0a4da12d7582e7d0500b1f55139584e70f310dac92b01b
-size 63516050

maiphuong.onnx.json DELETED Viewed

@@ -1 +0,0 @@

manhdung.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b5e4d3b55e02847082a07ddca34bccaca201bc83a4441b974accac699645bfe0
-size 63516050

manhdung.onnx.json DELETED Viewed

@@ -1 +0,0 @@

mattheo.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:959ff0d2759d4cafd33565f31007b895ccb29c4ef4cb504c048e66d7f36fe261
-size 63516050

mattheo1.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ca26161186b359de3bb4e28b2fe86a4e9658c02fe27f369fe5e9469c683b434c
-size 63516050

minhquang.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0a559df4c4eaab442e0d2007f32888f87567900dfe1a4e9f1632f64070090e17
-size 63516050

minhquang.onnx.json DELETED Viewed

@@ -1 +0,0 @@

mytam2.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:140f4b6f3c487338613f7c1b2842950110178404f7e9b5abed7640acd8956267
-size 63516050

mytam2.onnx.json DELETED Viewed

@@ -1 +0,0 @@

mytam2794.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a0c576d3366aa336ab56d782e2a0db174a26f6a1629cf418d2cf059d45ff6c1
-size 63516050

mytam2794.onnx.json DELETED Viewed

@@ -1 +0,0 @@

ngochuyen.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2140977786d76d834736c059dacfa553d4931dac2b2c7aaaea438bb2aa9da697
-size 63516050

ngochuyen.onnx.json DELETED Viewed

@@ -1 +0,0 @@

ngocngan3701.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c03a71201f51336fe937f12e54781520cb3bf629fa6adb3943314e29a58a9133
-size 63516050

ngocngan3701.onnx.json DELETED Viewed

@@ -1 +0,0 @@

phuongtrang.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:78e7f514503652a666e3e4b4d0d8fdc42f03d81a775a521b3119d1d7e6fc303f
-size 63516050

phuongtrang.onnx.json DELETED Viewed

@@ -1 +0,0 @@

taian1.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5daf1331d8481bad9f3804070416a84f0a5a0cc3493ee8910a275d623af4a871
-size 63516050

taian1.onnx.json DELETED Viewed

@@ -1 +0,0 @@

thanhphuong2.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f7d806e82e785729caf950893c2caa19a94ca79acfa1cd0deb2fc654cd61df68
-size 63516050

thanhphuong2.onnx.json DELETED Viewed

@@ -1 +0,0 @@

thientam.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2ac4616193b00c68d10997670ad617c6a3798a05262638b4811b2448e77c85dc
-size 63516050

thientam.onnx.json DELETED Viewed

@@ -1 +0,0 @@

tranthanh3870.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c3235ad51d99f5ce7d147ceb28db2ad2fe3500131d8ec77e804e6451ec293759
-size 63516050

tranthanh3870.onnx.json DELETED Viewed

@@ -1 +0,0 @@

vietthao3886.onnx DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f8cad266cfed6018390752326373379411b85efcfca21441e41e31a5aa4a6daf
-size 63516050

vietthao3886.onnx.json DELETED Viewed

@@ -1 +0,0 @@