Views
No views yet
instruction field uses the canonical pipe-separated trait spec from Vocence scoring (gender, pitch, speed, age_group, emotion, tone, accent with values like us / uk / au / in / neutral / other). text is what gets spoken.conds.pt, no audio_prompt_path): prosody follows instruction via mapped exaggeration / CFG / temperature / repetition_penalty. Ordinals on gender, accent, age_group are hard to satisfy without a reference clip—expect strongest alignment on emotion, tone, speed, pitch.| Method | Role |
|---|---|
Miner(path_hf_repo) | Loads ChatterboxTTS.from_local(repo) |
warmup() | Short synthesis |
generate_wav(instruction, text) | (float32 mono, sample_rate) — 24 kHz |
chatterbox.tts.ChatterboxTTS.from_local:ve.safetensors, t3_cfg.safetensors, s3gen.safetensors, tokenizer.json, conds.pt.safetensors files so their LFS blobs differ from an unmodified ResembleAI snapshot (subnet duplicate detection). Tensors stay identical; only __metadata__ / header changes:1python patch_chatterbox_safetensors_nonce.py
2# or per file: python ../../scripts/patch_safetensors_hf_metadata.py --in-place --nonce ve.safetensors1rsync -a --delete /path/to/hf_models/chatterbox/ ./Chatterbox-tts-v1/
2# or: huggingface-cli download ResembleAI/chatterbox --local-dir ./Chatterbox-tts-v1t3_mtl*.safetensors, etc.) are for multilingual builds; this bundle uses the English path only.miner_deploy_mad_tts_v1.py or scripts/publish_mad_tts_v1_to_hf.py to create the Hub repo and pin VOCENCE_REVISION. Chute id: vocence-mad-tts-v1. See VOCENCE_HF.md.1pip install chatterbox-tts torch torchaudio # CUDA wheel from chute_config.yml
2python -c "
3from pathlib import Path
4from miner import Miner
5m = Miner(Path('/path/to/chatterbox-weights'))
6m.warmup()
7w, sr = m.generate_wav('Calm, slightly slow delivery.', 'Hello from Chatterbox on Vocence.')
8print(w.shape, sr)
9"