Spaces:
Sleeping
Sleeping
| # MrrrMe Backend Requirements - Coqui XTTS v2 + emotion2vec | |
| # Core frameworks | |
| fastapi==0.115.4 | |
| uvicorn[standard]==0.32.0 | |
| python-multipart==0.0.12 | |
| websockets==13.1 | |
| # Computer Vision | |
| opencv-python-headless==4.10.0.84 | |
| pillow==11.0.0 | |
| scikit-image==0.24.0 | |
| matplotlib==3.9.2 | |
| timm==1.0.11 | |
| einops==0.8.0 | |
| # ML/DL | |
| # NOTE: torch, torchvision, torchaudio are installed in Dockerfile | |
| numpy==1.26.4 | |
| scipy==1.13.1 | |
| pandas==2.2.3 | |
| # Unpinned accelerate | |
| accelerate | |
| sentencepiece==0.2.0 | |
| safetensors==0.4.5 | |
| # Audio processing | |
| librosa==0.10.2.post1 | |
| soundfile==0.12.1 | |
| pyaudio==0.2.14 | |
| pydub==0.25.1 | |
| sounddevice==0.5.1 | |
| webrtcvad==2.0.10 | |
| # Voice Emotion Recognition (emotion2vec+ Large - 93% accuracy) | |
| # CRITICAL: Install funasr without dependencies to avoid gradio hell | |
| # funasr>=1.0.0 (Moved to Dockerfile manual install) | |
| # Manually install funasr dependencies (skipping gradio) | |
| # modelscope (Moved to Dockerfile manual install) | |
| kaldiio | |
| hydra-core | |
| editdistance | |
| jieba | |
| torch-complex | |
| pytorch-wpe | |
| # Text-to-Speech (Qwen 3 TTS via transformers) | |
| qwen-tts | |
| # Transformers: Qwen TTS requires a very recent version (e.g. 4.57.3) | |
| transformers | |
| # accelerate is already listed above | |
| # Text processing | |
| nltk==3.9.1 | |
| # Groq API | |
| groq==0.14.0 | |
| # Utilities | |
| requests==2.32.3 | |
| python-dotenv==1.0.1 | |
| huggingface_hub>=0.20.0 | |
| tensorboardX==2.6.2.2 |