Instructions to use 3scale/VoxCPM2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VoxCPM
How to use 3scale/VoxCPM2 with VoxCPM:
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("3scale/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
update architecture from "voxcpm2" to VoxCPMForConditionalGeneration
Browse files- config.json +3 -1
config.json
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
| 3 |
"lm_config": {
|
| 4 |
"bos_token_id": 1,
|
| 5 |
"eos_token_id": 2,
|
|
|
|
| 1 |
{
|
| 2 |
+
"model_type": "voxcpm",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VoxCPMForConditionalGeneration"],
|
| 5 |
"lm_config": {
|
| 6 |
"bos_token_id": 1,
|
| 7 |
"eos_token_id": 2,
|