pseudoram/rvc-v2 🔢❓🖼️📝 → 🖼️

▶️ 1.5M runs 📅 Jun 2024 ⚙️ Cog 0.9.10 🔗 GitHub ⚖️ License

audio-to-audio speech-style-transfer voice-cloning voice-conversion

Performance

8.0sTypical run time

1.5MTotal runs

About

Speech to speech with any RVC v2 trained AI voice

Example Output

Output

Performance Metrics

8.01s Prediction Time

8.05s Total Time

All Input Parameters

{
  "protect": 0.5,
  "f0_method": "rmvpe",
  "rvc_model": "CUSTOM",
  "index_rate": 1,
  "input_audio": "https://replicate.delivery/pbxt/LAxQbQLiKJZevqiV9Raodpdd6W0ihu3Wnb1K6xCpE6rcUIu5/ttsMP3.com_VoiceText_2024-6-29_0-22-2.mp3",
  "pitch_change": 8,
  "rms_mix_rate": 1,
  "filter_radius": 1,
  "output_format": "mp3",
  "crepe_hop_length": 128,
  "custom_rvc_model_download_url": "https://huggingface.co/Argax/doofenshmirtz-RUS/resolve/main/doofenshmirtz.zip"
}

Input Parameters

protect Type: numberDefault: 0.33Range: 0 - 0.5: Control how much of the original vocals' breath and voiceless consonants to leave in the AI vocals. Set 0.5 to disable.
f0_method Default: rmvpe: Pitch detection algorithm. 'rmvpe' for clarity in vocals, 'mangio-crepe' for smoother vocals.
rvc_model Default: Obama: RVC model for a specific voice. If using a custom model, this should match the name of the downloaded model. If a 'custom_rvc_model_download_url' is provided, this will be automatically set to the name of the downloaded model.
index_rate Type: numberDefault: 0.5Range: 0 - 1: Control how much of the AI's accent to leave in the vocals.
input_audio Type: string: Upload your audio file here.
pitch_change Type: numberDefault: 0: Adjust pitch of AI vocals in semitones. Use positive values to increase pitch, negative to decrease.
rms_mix_rate Type: numberDefault: 0.25Range: 0 - 1: Control how much to use the original vocal's loudness (0) or a fixed loudness (1).
filter_radius Type: integerDefault: 3Range: 0 - 7: If >=3: apply median filtering to the harvested pitch results.
output_format Default: mp3: wav for best quality and large file size, mp3 for decent quality and small file size.
crepe_hop_length Type: integerDefault: 128: When `f0_method` is set to `mangio-crepe`, this controls how often it checks for pitch changes in milliseconds.
custom_rvc_model_download_url Type: string: URL to download a custom RVC model. If provided, the model will be downloaded (if it doesn't already exist) and used for prediction, regardless of the 'rvc_model' value.

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

[!] The model will be downloaded as 'doofenshmirtz'.
[!] Voice model directory doofenshmirtz already exists. Overwriting...
[*] Downloading model from https://huggingface.co/Argax/doofenshmirtz-RUS/resolve/main/doofenshmirtz.zip...
[*] Extracting model to /src/rvc_models/doofenshmirtz...
2024-06-28 15:49:59 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src
2024-06-28 15:49:59 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False}
2024-06-28 15:49:59 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False}
gin_channels: 256 self.spk_embed_dim: 109
<All keys matched successfully>
[+] Converted audio generated at /src/voice_output/converted_tmp_fayvycvttsMP3.com_VoiceText_2024-6-29_0-22-2.wav

Version Details

Version ID: d18e2e0a6a6d3af183cc09622cebba8555ec9a9e66983261fc64c8b1572b7dce
Version Created: June 28, 2024

Run on Replicate →