| numpy<2.0 | |
| scipy | |
| tensorboard | |
| librosa==0.9.2 | |
| numba | |
| pytorch-lightning>=2.4 | |
| gradio>=4.41,<5 | |
| ffmpeg-python | |
| onnxruntime; sys_platform == 'darwin' | |
| onnxruntime-gpu; sys_platform != 'darwin' | |
| tqdm | |
| funasr==1.0.27 | |
| cn2an | |
| pypinyin | |
| pyopenjtalk>=0.4.1 | |
| g2p_en | |
| torchaudio | |
| modelscope==1.10.0 | |
| sentencepiece | |
| transformers>=4.43 | |
| peft | |
| chardet | |
| PyYAML | |
| psutil | |
| jieba_fast | |
| jieba | |
| split-lang | |
| fast_langdetect>=0.3.1 | |
| wordsegment | |
| rotary_embedding_torch | |
| ToJyutping | |
| g2pk2 | |
| ko_pron | |
| opencc; sys_platform != 'linux' | |
| opencc==1.1.1; sys_platform == 'linux' | |
| python_mecab_ko; sys_platform != 'win32' | |
| fastapi[standard]>=0.115.1 | |
| x_transformers | |
| torchmetrics<=1.5 | |
| pydantic<=2.10.6 | |
| ctranslate2>=4.0,<5 | |
| huggingface_hub>=0.13 | |
| tokenizers>=0.13,<1 | |
| av>=11 | |
| tqdm | |