| torch>=2.1.0 | |
| torchvision>=0.16.0 | |
| torchaudio>=2.1.0 | |
| numpy>=1.24.0 | |
| transformers>=4.41.0 | |
| accelerate>=0.30.0 | |
| datasets>=2.18.0 | |
| timm>=0.9.0 | |
| soundfile>=0.12.1 | |
| librosa>=0.10.0 | |
| gradio>=4.0.0 | |
| phonemizer>=3.2 | |
| Pillow>=9.5.0 | |
| gTTS>=2.5.1 | |
| torch>=2.1.0 | |
| torchvision>=0.16.0 | |
| torchaudio>=2.1.0 | |
| numpy>=1.24.0 | |
| transformers>=4.41.0 | |
| accelerate>=0.30.0 | |
| datasets>=2.18.0 | |
| timm>=0.9.0 | |
| soundfile>=0.12.1 | |
| librosa>=0.10.0 | |
| gradio>=4.0.0 | |
| phonemizer>=3.2 | |
| Pillow>=9.5.0 | |
| gTTS>=2.5.1 | |