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
cross-lingual transfer without an accent
#14
by Markobes - opened
I have tested VoxCPM2, and in the Gradio interface, I noticed that the Ultimate Cloning Mode (transcript-guided cloning) results in a noticeable accent in the generated audio in another language. However, the Control Instruction allows you to specify the target language of the generated audio and largely eliminate the accent. Can the Ultimate Cloning Mode perform cross-lingual transfer without an accent in basically when this mode is used by the API?
Thanks