Instructions to use Praha-Labs/PrahaTTS-ML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chatterbox
How to use Praha-Labs/PrahaTTS-ML with Chatterbox:
# pip install chatterbox-tts import torchaudio as ta from chatterbox.tts import ChatterboxTTS model = ChatterboxTTS.from_pretrained(device="cuda") text = "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill." wav = model.generate(text) ta.save("test-1.wav", wav, model.sr) # If you want to synthesize with a different voice, specify the audio prompt AUDIO_PROMPT_PATH="YOUR_FILE.wav" wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH) ta.save("test-2.wav", wav, model.sr) - Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| language: | |
| - ml | |
| base_model: ResembleAI/chatterbox | |
| tags: | |
| - text-to-speech | |
| - tts | |
| - malayalam | |
| - chatterbox | |
| - lora | |
| # PrahaTTS-ML | |
| Malayalam LoRA adapter for ResembleAI Chatterbox non-turbo TTS. | |
| This repository contains the selected 17k-step adapter checkpoint, chosen by listening quality rather than lowest training loss. | |
| ## Contents | |
| - `adapter_config.json` | |
| - `adapter_model.safetensors` | |
| - `tokenizer_indic.json` | |
| - `tokenizer_indic.json.manifest.json` | |
| - `config_indic.py` | |
| This is not a merged full model. Use it with the base Chatterbox non-turbo model and the included Indic tokenizer. | |