Instructions to use openbmb/VoxCPM2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VoxCPM
How to use openbmb/VoxCPM2 with VoxCPM:
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("openbmb/VoxCPM2") wav = model.generate( text="VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.", prompt_wav_path=None, # optional: path to a prompt speech for voice cloning prompt_text=None, # optional: reference text cfg_value=2.0, # LM guidance on LocDiT, higher for better adherence to the prompt, but maybe worse inference_timesteps=10, # LocDiT inference timesteps, higher for better result, lower for fast speed normalize=True, # enable external TN tool denoise=True, # enable external Denoise tool retry_badcase=True, # enable retrying mode for some bad cases (unstoppable) retry_badcase_max_times=3, # maximum retrying times retry_badcase_ratio_threshold=6.0, # maximum length restriction for bad case detection (simple but effective), it could be adjusted for slow pace speech ) sf.write("output.wav", wav, 16000) print("saved: output.wav") - Notebooks
- Google Colab
- Kaggle
音色设计产生的音频再次用于复刻时的问题
#10
by eldzwdkl - opened
您好,我将音色设计产生的音频用于声音克隆时,会出现kv_cache持续累积“误差”使得后面的音频出现越来越大的“嗡嗡”的声音。
我不是专业做这个的,但我非常想快速解决这个问题,于是我用了可能有隐患的临时方法。
请问这个“嗡嗡”的声音是什么?是因为合成的声音和真人声音有差异,所以造成音质下降的情形吗?
请问这个的标准解决方法应该是什么?
我的临时解决方法是:
回看 1 步方法(干净特征传递):
句子1: 原始cache → wav_1 + clean_feat_1 (1次推理)
句子2:
Pass 1: 原始cache → clean_feat_2 (干净特征,音频丢弃)
Pass 2: 原始cache + clean_feat_1 → wav_2 (实际输出)
句子3:
Pass 1: 原始cache → clean_feat_3 (干净特征,音频丢弃)
Pass 2: 原始cache + clean_feat_2 → wav_3 (实际输出)
拼接
这个方法能有效的在“使用合成的声音进行克隆”时,提高音频的品质。
和您一样的问题