111 lines
4.6 KiB
Plaintext
111 lines
4.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"2024-03-31 05:59:31 | INFO | fairseq.tasks.text_to_speech | Please install tensorboardX: pip install tensorboardX\n",
|
|
"2024-03-31 05:59:32 | INFO | faiss.loader | Loading faiss with AVX2 support.\n",
|
|
"2024-03-31 05:59:32 | INFO | faiss.loader | Successfully loaded faiss with AVX2 support.\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from main import song_cover_pipeline"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" % Total % Received % Xferd Average Speed Time Time Time Current\n",
|
|
" Dload Upload Total Spent Left Speed\n",
|
|
"100 90234 100 90234 0 0 1190k 0 --:--:-- --:--:-- --:--:-- 1174k\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"!curl -o '../audio/input.ogg' 'https://cdn.discordapp.com/attachments/252959763841679360/1222430418847010868/voice-message.ogg?ex=6616300b&is=6603bb0b&hm=edb5794314702eb535d16e96841587492033420c18e4e2b647947665109d172a&'"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Output file path will be: ../audio/input_miku_p12_i0.5_fr3_rms0.25_pro0.33_rmvpe.wav\n",
|
|
"[~] Converting voice using RVC...\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"2024-03-31 05:59:45 | INFO | fairseq.tasks.hubert_pretraining | current directory is /home/jshiffer/rvc\n",
|
|
"2024-03-31 05:59:45 | 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}\n",
|
|
"2024-03-31 05:59:45 | 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}\n",
|
|
"/opt/conda/envs/rvc/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\n",
|
|
" warnings.warn(\"torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\")\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"gin_channels: 256 self.spk_embed_dim: 109\n",
|
|
"<All keys matched successfully>\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'../audio/input_miku_p12_i0.5_fr3_rms0.25_pro0.33_rmvpe.wav'"
|
|
]
|
|
},
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"song_cover_pipeline('../audio/input.ogg', 1)"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "rvc",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.10.14"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|