Instructions to use iliasaz/chatterbox-multilingual-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chatterbox
How to use iliasaz/chatterbox-multilingual-coreml 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
Commit History
30 days ago
-
S3Encoder: exact int32 positional-encoding bounds
Verified signatureThe exported encoder computed its positional-encoding slice bounds (pe.size(1)//2 -/+ T) in fp16, with the centre 4999 baked as 5000, so the slice was exact only when T%4==0 (the SynthRunner pad-to-%4 masked it; otherwise cos ~0.97-0.99 vs PyTorch). Rewrites the 12 ops + 6 consts to int32 with the exact centre 4999. Weights unchanged. cos >= 0.99997 vs the PyTorch multilingual encoder for T in 100..1020 incl. non-multiples of 4, CPU and ANE. (This export has no fp16 rel-shift arithmetic, so unlike turbo/nano it did not fail outright on iOS/macOS 27.)295edc7
-
Multilingual (Russian) CoreML bundle: T3LM + host tables + S3 synth + cloning encoders + grapheme tokenizer
Verified signature18faa6a