Views
No views yet
model_name in vocence_config.yaml, on-chain commit, and chute wrapper VOCENCE_REPO must all be:shiningstar1128/monkey_01/speak contract1{
2 "text": "<transcription to synthesize>",
3 "instruction": "An adult female with an American accent, speaking at a normal pace in a mid-range pitch, sounding neutral and formal throughout"
4}text — passed verbatim as the synthesis script (length cap only).instruction — passed verbatim to the processor system_prompt (length cap only).instruction → processor system_prompt (no trait parsing or paraphrasing).text → script body (plain transcript or existing Speaker N: lines).| File | Purpose |
|---|---|
miner.py | QWEN3Vox engine (Miner class) |
vocence_config.yaml | model_name + runtime/generation limits |
chute_config.yml | Chutes image, GPU (64 GB VRAM), pip deps |
model-0000*-of-00003.safetensors | Sharded weights (≥ 50 MiB total) |
aux_lm_residual_projection.safetensors | Aux conditioning shard |
tokenizer.json, tokenizer_config.json, vocab.json, merges.txt | Tokenizer |
shiningstar1128/monkey_01 and pin a 40-char commit SHA.VOCENCE_REPO=shiningstar1128/monkey_01.uv run vocence miner commit --model-name shiningstar1128/monkey_01 --model-revision <sha> --chute-id <uuid>.