| # IndexTTS Requirements for HuggingFace Spaces (CPU-only) | |
| accelerate==1.8.1 | |
| cn2an==0.5.22 | |
| cython==3.0.7 | |
| descript-audiotools==0.7.2 | |
| einops>=0.8.1 | |
| ffmpeg-python==0.2.0 | |
| g2p-en==2.1.0 | |
| jieba==0.42.1 | |
| json5==0.10.0 | |
| keras==2.9.0 | |
| librosa==0.10.2.post1 | |
| matplotlib==3.8.2 | |
| modelscope==1.27.0 | |
| munch==4.0.0 | |
| numba==0.58.1 | |
| numpy==1.26.2 | |
| omegaconf>=2.3.0 | |
| opencv-python==4.9.0.80 | |
| pandas==2.3.2 | |
| safetensors==0.5.2 | |
| sentencepiece>=0.2.1 | |
| soundfile==0.12.1 | |
| tensorboard==2.9.1 | |
| textstat>=0.7.10 | |
| tokenizers==0.21.0 | |
| torch==2.8.* | |
| torchaudio==2.8.* | |
| tqdm>=4.67.1 | |
| transformers==4.52.1 | |
| gradio==5.45.0 | |
| huggingface_hub | |
| # Text processing for different platforms | |
| wetext>=0.0.9; sys_platform != 'linux' | |
| WeTextProcessing; sys_platform == 'linux' | |
| # Note: DeepSpeed excluded for CPU-only deployment |