ViZipvoice

--- license: apache-2.0 language: - vi library_name: pytorch pipeline_tag: text-to-speech tags: - text-to-speech - zero-shot-tts - voice-cloning - vietnamese - zipvoice base_model: k2-fsa/ZipVoice --- # ViZipVoice Vietnamese zero-shot TTS / voice cloning fine-tuned from [ZipVoice](https://github.com/k2-fsa/ZipVoice). - GitHub: https://github.com/iamdinhthuan/ViZipvoice - Model repo: https://huggingface.co/contextboxai/ViZipvoice - Space: https://huggingface.co/spaces/dinhthuan/ViZipvoice - Latest checkpoint: `checkpoint-1860000.pt`, FP16 inference state dict - Training data: about `7000` total hours, including roughly `6500` hours of Vietnamese and `500` hours of English - Tokenizer: `SimpleTokenizer`, character-level, `244` tokens - Sample rate: `24 kHz` - Default vocoder: `charactr/vocos-mel-24khz` The wrapper loads the largest `checkpoint-<step>.pt` automatically and uses `soe-vinorm` for Vietnamese text normalization. ## Audio Demo Generated with `checkpoint-1860000.pt`, the current wrapper flow, and the demo text in `demo/demo_text.txt`. **Đinh-Quyết** <audio controls src="https://huggingface.co/contextboxai/ViZipvoice/resolve/main/demo/demo_01_%C4%90inh-Quy%E1%BA%BFt.wav"></audio> [Open audio](https://huggingface.co/contextboxai/ViZipvoice/resolve/main/demo/demo_01_%C4%90inh-Quy%E1%BA%BFt.wav) **Nhã-Uyên** <audio controls src="https://huggingface.co/contextboxai/ViZipvoice/resolve/main/demo/demo_02_Nh%C3%A3-Uy%C3%AAn.wav"></audio> [Open audio](https://huggingface.co/contextboxai/ViZipvoice/resolve/main/demo/demo_02_Nh%C3%A3-Uy%C3%AAn.wav) **MC** <audio controls src="https://huggingface.co/contextboxai/ViZipvoice/resolve/main/demo/demo_03_MC.wav"></audio> [Open audio](https://huggingface.co/contextboxai/ViZipvoice/resolve/main/demo/demo_03_MC.wav) ## Install ```bash git clone https://github.com/iamdinhthuan/ViZipvoice.git cd ViZipvoice pip install -r requirements.txt export PYTHONPATH="$PWD:$PYTHONPATH" ``` ## CLI ```bash python3 -m zipvoice.bin.infer_vizipvoice \ --prompt-wav prompt.wav \ --prompt-text "Xin chào, đây là giọng mẫu của tôi." \ --text "ViZipVoice có thể tổng hợp giọng nói tiếng Việt từ một đoạn mẫu ngắn." \ --res-wav-path output.wav ``` The CLI downloads this model repo by default. Use `--model-dir models/ViZipvoice` after downloading files locally. ## Python ```python from zipvoice.vizipvoice import ViZipVoic...

Source context: 513 downloads · 6 likes · Pipeline text-to-speech · Library pytorch · Repo contextboxai/ViZipvoice