| # Core dependencies |
| gradio>=4.0.0 |
| torch>=2.0.0 |
| torchaudio>=2.0.0 |
| transformers>=4.30.0 |
| huggingface-hub>=0.20.0 |
|
|
| # Numerical and scientific computing |
| numpy<2.0.0 |
| scipy>=1.10.0 |
|
|
| # Audio processing |
| librosa>=0.10.0 |
| soundfile>=0.12.0 |
| soxr |
| pydub |
|
|
| # ML and deep learning |
| onnxruntime>=1.15.0 |
| einops>=0.7.0 |
| timm>=0.9.0 |
| safetensors |
| accelerate |
| sentencepiece |
| protobuf |
|
|
| # Configuration and utilities |
| pyyaml>=6.0 |
| hydra-core>=1.3.0 |
| omegaconf>=2.3.0 |
|
|
| # Visualization |
| matplotlib>=3.7.0 |
| tensorboard |
| tensorboardX |
|
|
| # Audio features |
| kaldiio |
|
|
| # Text processing - Chinese |
| pypinyin |
| jieba |
| cn2an |
| opencc-python-reimplemented |
| WeTextProcessing |
|
|
| # Text processing - English |
| inflect |
| eng_to_ipa |
| unidecode |
| g2p_en |
| contractions |
|
|
| # Utilities |
| regex |
| tqdm |
| requests |
| modelscope |
| onnx |
