Instructions to use mlboydaisuke/VoxCPM2-CoreAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VoxCPM
How to use mlboydaisuke/VoxCPM2-CoreAI with VoxCPM:
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("mlboydaisuke/VoxCPM2-CoreAI") 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
File size: 1,683 Bytes
e91f209 | 1 | {"storageTypes":[{"name":"Int8","count":1321216000},{"count":780291,"name":"Float16"},{"name":"Int32","count":838},{"name":"UInt32","count":55},{"name":"Float32","count":3},{"count":1,"name":"UInt64"}],"computeTypes":["Bool","Float16","Float32","Int32","Int8","UInt32","UInt64"],"operationDistribution":[{"count":3252,"name":"constant"},{"count":653,"name":"reshape"},{"name":"broadcast_in_dims","count":426},{"count":424,"name":"mul"},{"count":371,"name":"cast"},{"count":367,"name":"broadcasting_mul"},{"name":"add","count":311},{"name":"broadcast_to","count":282},{"count":280,"name":"concat"},{"count":253,"name":"blockwise_shift_scale"},{"count":252,"name":"batch_matmul"},{"count":252,"name":"broadcasting_batch_matmul"},{"count":226,"name":"broadcasting_add"},{"count":224,"name":"slice"},{"name":"transpose","count":224},{"count":142,"name":"reduce"},{"count":113,"name":"broadcasting_divide"},{"name":"divide","count":113},{"name":"reduce_sum","count":85},{"name":"gather_along_axis","count":58},{"count":58,"name":"read_handle"},{"count":57,"name":"broadcast_shapes"},{"count":57,"name":"broadcasting_pow"},{"count":57,"name":"gather_nd"},{"name":"get_shape","count":57},{"count":57,"name":"pow"},{"count":57,"name":"reduce_mean"},{"count":57,"name":"reduce_product"},{"name":"rsqrt","count":57},{"count":56,"name":"exp"},{"name":"slice_update","count":56},{"name":"split","count":56},{"count":56,"name":"write_handle"},{"name":"broadcasting_sub","count":28},{"name":"silu","count":28},{"name":"softmax","count":28},{"count":28,"name":"sub"},{"count":2,"name":"not"},{"name":"broadcasting_greater","count":1},{"count":1,"name":"create_token"},{"name":"greater","count":1}]} |