Spaces:
Running
Running
TTS: Oute 1B added
Browse files- README.md +2 -1
- app/messages.py +0 -2
- app/models.py +18 -2
README.md
CHANGED
|
@@ -29,4 +29,5 @@ models:
|
|
| 29 |
sdk_version: 5.4.0
|
| 30 |
---
|
| 31 |
|
| 32 |
-
[Saved votes](https://huggingface.co/datasets/Pendrokar/
|
|
|
|
|
|
| 29 |
sdk_version: 5.4.0
|
| 30 |
---
|
| 31 |
|
| 32 |
+
[Saved votes dataset](https://huggingface.co/datasets/Pendrokar/TTS_Arena)
|
| 33 |
+
[TTS tracker dataset](https://huggingface.co/datasets/Pendrokar/open_tts_tracker)
|
app/messages.py
CHANGED
|
@@ -81,8 +81,6 @@ except:
|
|
| 81 |
pass
|
| 82 |
|
| 83 |
TTS_INFO = f"""
|
| 84 |
-
## 🗣 Contenders
|
| 85 |
-
|
| 86 |
### 🔐 Closed Source TTS
|
| 87 |
* Microsoft _Edge TTS_
|
| 88 |
|
|
|
|
| 81 |
pass
|
| 82 |
|
| 83 |
TTS_INFO = f"""
|
|
|
|
|
|
|
| 84 |
### 🔐 Closed Source TTS
|
| 85 |
* Microsoft _Edge TTS_
|
| 86 |
|
app/models.py
CHANGED
|
@@ -64,6 +64,8 @@ AVAILABLE_MODELS = {
|
|
| 64 |
# OuteTTS
|
| 65 |
# 'OuteAI/OuteTTS-0.2-500M-Demo': 'OuteAI/OuteTTS-0.2-500M-Demo',
|
| 66 |
'ameerazam08/OuteTTS-0.2-500M-Demo': 'ameerazam08/OuteTTS-0.2-500M-Demo', # ZeroGPU Space
|
|
|
|
|
|
|
| 67 |
|
| 68 |
# HF TTS w issues
|
| 69 |
# 'LeeSangHoon/HierSpeech_TTS': 'LeeSangHoon/HierSpeech_TTS', # irresponsive to exclamation marks # 4.29
|
|
@@ -272,7 +274,7 @@ HF_SPACES = {
|
|
| 272 |
'emoji': '🥵', # 300s minimum ZeroGPU!
|
| 273 |
},
|
| 274 |
'lj1995/GPT-SoVITS-v2': {
|
| 275 |
-
'name': 'GPT-SoVITS',
|
| 276 |
'function': '/get_tts_wav',
|
| 277 |
'text_param_index': 'text',
|
| 278 |
'return_audio_index': 0,
|
|
@@ -280,13 +282,21 @@ HF_SPACES = {
|
|
| 280 |
'series': 'GPT-SoVITS',
|
| 281 |
},
|
| 282 |
'ameerazam08/OuteTTS-0.2-500M-Demo': {
|
| 283 |
-
'name': 'OuteTTS
|
| 284 |
'function': '/generate_tts',
|
| 285 |
'text_param_index': 0,
|
| 286 |
'return_audio_index': 0,
|
| 287 |
'is_zero_gpu_space': True,
|
| 288 |
'series': 'OuteTTS',
|
| 289 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 290 |
}
|
| 291 |
|
| 292 |
# for zero-shot TTS - voice sample used by XTTS (11 seconds)
|
|
@@ -454,6 +464,12 @@ OVERRIDE_INPUTS = {
|
|
| 454 |
5: None, # reference_audio
|
| 455 |
6: None, # reference_text
|
| 456 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 457 |
}
|
| 458 |
|
| 459 |
|
|
|
|
| 64 |
# OuteTTS
|
| 65 |
# 'OuteAI/OuteTTS-0.2-500M-Demo': 'OuteAI/OuteTTS-0.2-500M-Demo',
|
| 66 |
'ameerazam08/OuteTTS-0.2-500M-Demo': 'ameerazam08/OuteTTS-0.2-500M-Demo', # ZeroGPU Space
|
| 67 |
+
# OuteTTS 1B
|
| 68 |
+
'OuteAI/OuteTTS-0.3-1B-Demo': 'OuteAI/OuteTTS-0.3-1B-Demo',
|
| 69 |
|
| 70 |
# HF TTS w issues
|
| 71 |
# 'LeeSangHoon/HierSpeech_TTS': 'LeeSangHoon/HierSpeech_TTS', # irresponsive to exclamation marks # 4.29
|
|
|
|
| 274 |
'emoji': '🥵', # 300s minimum ZeroGPU!
|
| 275 |
},
|
| 276 |
'lj1995/GPT-SoVITS-v2': {
|
| 277 |
+
'name': 'GPT-SoVITS v2',
|
| 278 |
'function': '/get_tts_wav',
|
| 279 |
'text_param_index': 'text',
|
| 280 |
'return_audio_index': 0,
|
|
|
|
| 282 |
'series': 'GPT-SoVITS',
|
| 283 |
},
|
| 284 |
'ameerazam08/OuteTTS-0.2-500M-Demo': {
|
| 285 |
+
'name': 'OuteTTS v2 500M',
|
| 286 |
'function': '/generate_tts',
|
| 287 |
'text_param_index': 0,
|
| 288 |
'return_audio_index': 0,
|
| 289 |
'is_zero_gpu_space': True,
|
| 290 |
'series': 'OuteTTS',
|
| 291 |
},
|
| 292 |
+
'OuteAI/OuteTTS-0.3-1B-Demo': {
|
| 293 |
+
'name': 'OuteTTS v3 1B',
|
| 294 |
+
'function': '/generate_tts',
|
| 295 |
+
'text_param_index': 'text',
|
| 296 |
+
'return_audio_index': 0,
|
| 297 |
+
'is_zero_gpu_space': True,
|
| 298 |
+
'series': 'OuteTTS',
|
| 299 |
+
},
|
| 300 |
}
|
| 301 |
|
| 302 |
# for zero-shot TTS - voice sample used by XTTS (11 seconds)
|
|
|
|
| 464 |
5: None, # reference_audio
|
| 465 |
6: None, # reference_text
|
| 466 |
},
|
| 467 |
+
'OuteAI/OuteTTS-0.3-1B-Demo': {
|
| 468 |
+
'temperature': 0.1,
|
| 469 |
+
'repetition_penalty': 1.1,
|
| 470 |
+
'speaker_selection': "en_female_1",
|
| 471 |
+
'reference_audio': None,
|
| 472 |
+
},
|
| 473 |
}
|
| 474 |
|
| 475 |
|