lora微调训练的时候指定了ref_audio，infer的时候怎么用这个ref_audio？
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 37.8k
- Forks
- 4.3k
- Avg merge
- 7m
- Merged PRs (30d)
- 1
Description
lora微调训练的时候指定了ref_audio，infer的时候怎么用这个ref_audio？
我看lora训练完后给的两个infer模式里，都没包含ref_audio的模式：求帮忙解答一下哈。另外这个ref_audio对于每个spk都是固定一条吗？
1、CLI
python scripts/test_voxcpm_lora_infer.py
--lora_ckpt /path/to/checkpoints/lora/step_0002000
--text "Hello from the fine-tuned model."
--output output.wav
2、Python API
from voxcpm import VoxCPM
model = VoxCPM.from_pretrained(
"openbmb/VoxCPM2",
lora_weights_path="/path/to/checkpoints/lora/latest",
)
wav = model.generate(text="Hello from the fine-tuned model.")
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with scripts/test_voxcpm_lora_infer.py and the VoxCPM.from_pretrained/generate example, then trace how ref_audio is handled during LoRA training and inference. Document whether ref_audio can be supplied through the CLI and Python API, and clarify whether each speaker needs a fixed reference audio. Done means both inference paths have a reproducible usage example.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100