Spaces:
Build error
Build error
| # --- Core runtime / serving --- | |
| gradio>=4.0 | |
| fastapi>=0.115 | |
| uvicorn[standard]>=0.30 | |
| huggingface_hub>=0.24 | |
| python-dotenv>=1.0 | |
| # --- PyTorch trio (CPU-friendly) --- | |
| torch==2.3.1 | |
| torchaudio==2.3.1 | |
| torchvision==0.18.1 | |
| # --- Scientific / ML backbone --- | |
| numpy>=1.26,<3 | |
| scipy>=1.11 | |
| scikit-learn>=1.3 | |
| pandas>=2.2 | |
| matplotlib>=3.8 | |
| numba>=0.59 | |
| llvmlite>=0.43 | |
| tqdm>=4.66 | |
| einops>=0.7 | |
| protobuf>=4.24 | |
| safetensors>=0.4.3 | |
| # --- NLP / Transformers / Whisper --- | |
| transformers==4.55.4 | |
| tokenizers>=0.15 | |
| sentencepiece>=0.1.99 | |
| #faster-whisper==1.2.0 | |
| #whisperx==3.7.4 | |
| #whisper==1.1.10 | |
| nltk>=3.9 | |
| regex>=2024.9.11 | |
| # --- Audio / TTS / ASR toolchain --- | |
| soundfile>=0.12 | |
| audioread>=3.0.1 | |
| soxr>=0.3.7 | |
| ffmpeg-python>=0.2.0 | |
| pydub>=0.25.1 | |
| audiostretchy==1.3.5 | |
| demucs==4.0.1 | |
| openunmix==1.3.0 | |
| asteroid-filterbanks==0.4.0 | |
| pytorch-wpe==0.0.1 | |
| speechbrain==1.0.3 | |
| coqui-tts==0.27.2 | |
| coqpit-config==0.2.1 | |
| ttsfrd==0.1.0 | |
| edge-tts==7.2.3 | |
| librosa==0.11.0 | |
| soxr>=0.3.7 | |
| # --- Diffusion / audio codecs (if you actually use them) --- | |
| diffusers==0.27.2 | |
| encodec==0.1.1 | |
| # --- Model management / orchestration --- | |
| accelerate==1.11.0 | |
| hydra-core==1.3.2 | |
| omegaconf==2.3.0 | |
| lightning==2.5.5 | |
| pytorch-lightning==2.5.5 | |
| torchmetrics==1.3.2 | |
| # --- PyAnnote (diarization) --- | |
| pyannote.audio==3.4.0 | |
| pyannote.core==5.0.0 | |
| pyannote.database==5.1.3 | |
| pyannote.metrics==3.2.1 | |
| pyannote.pipeline==3.0.1 | |
| # --- OpenAI / HTTP clients --- | |
| openai==1.55.3 | |
| httpx>=0.27 | |
| requests>=2.31 | |
| urllib3>=2.2 | |
| # --- Data / storage / utils --- | |
| orjson>=3.10 | |
| ujson>=5.9 | |
| pyarrow>=16.0 | |
| zstandard>=0.22 | |
| cloudpickle>=3.0 | |
| joblib>=1.3 | |
| filelock>=3.12 | |
| rich>=13.7 | |
| tabulate>=0.9 | |
| Unidecode>=1.3 | |
| # --- Text processing / multi-language --- | |
| pypinyin>=0.49 | |
| jieba>=0.42.1 | |
| jaconv>=0.4 | |
| SudachiPy>=0.6.8 | |
| SudachiDict-core>=20240109 | |
| WeTextProcessing>=1.0.3 | |
| pysbd>=0.3.4 | |
| bangla==0.0.5 | |
| bnunicodenormalizer==0.1.7 | |
| bnnumerizer==0.0.2 | |
| # --- Misc ML / optimization --- | |
| optuna>=3.6 | |
| pytorch-metric-learning>=2.3 | |
| umap-learn>=0.5.5 | |
| pynndescent>=0.5.10 | |
| # --- Media / video --- | |
| moviepy>=1.0.3 | |
| imageio>=2.34 | |
| imageio-ffmpeg>=0.4.9 | |
| av>=10.0 | |
| # --- Small helpers (stable) --- | |
| loguru>=0.7 | |
| fire>=0.6 | |
| packaging>=23.2 | |
| typing_extensions>=4.9 | |
| python-dateutil>=2.8.2 | |
| pytz>=2024.1 | |
| tzlocal>=5.2 | |
| PyYAML>=6.0.1 | |
| regex>=2024.9.11 | |
| # --- Optional (comment out if not needed) --- | |
| onnxruntime==1.23.1 | |
| translators==6.0.1 | |
| gdown==5.1.0 | |
| yt-dlp>=2024.5.27 | |
| openunmix==1.3.0 | |
| demucs>=4.0.0 | |
| TTS | |