Instructions to use thiicarry/VoxCPM2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VoxCPM
How to use thiicarry/VoxCPM2 with VoxCPM:
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("thiicarry/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
| { | |
| "architecture": "voxcpm2", | |
| "lm_config": { | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_size": 2048, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 32768, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000, | |
| "kv_channels": 128, | |
| "rope_scaling": { | |
| "type": "longrope", | |
| "long_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529], | |
| "short_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529], | |
| "original_max_position_embeddings": 32768 | |
| }, | |
| "vocab_size": 73448, | |
| "use_mup": false, | |
| "scale_emb": 12, | |
| "dim_model_base": 256, | |
| "scale_depth": 1.4 | |
| }, | |
| "patch_size": 4, | |
| "feat_dim": 64, | |
| "scalar_quantization_latent_dim": 512, | |
| "scalar_quantization_scale": 9, | |
| "residual_lm_num_layers": 8, | |
| "residual_lm_no_rope": true, | |
| "encoder_config": { | |
| "hidden_dim": 1024, | |
| "ffn_dim": 4096, | |
| "num_heads": 16, | |
| "num_layers": 12, | |
| "kv_channels": 128 | |
| }, | |
| "dit_config": { | |
| "hidden_dim": 1024, | |
| "ffn_dim": 4096, | |
| "num_heads": 16, | |
| "num_layers": 12, | |
| "kv_channels": 128, | |
| "mean_mode": false, | |
| "cfm_config": { | |
| "sigma_min": 1e-06, | |
| "solver": "euler", | |
| "t_scheduler": "log-norm", | |
| "inference_cfg_rate": 2.0 | |
| } | |
| }, | |
| "audio_vae_config": { | |
| "encoder_dim": 128, | |
| "encoder_rates": [2, 5, 8, 8], | |
| "latent_dim": 64, | |
| "decoder_dim": 2048, | |
| "decoder_rates": [8, 6, 5, 2, 2, 2], | |
| "sr_bin_boundaries": [20000, 30000, 40000], | |
| "sample_rate": 16000, | |
| "out_sample_rate": 48000 | |
| }, | |
| "max_length": 8192, | |
| "device": "cuda", | |
| "dtype": "bfloat16" | |
| } | |