Spaces:
Sleeping
Sleeping
Initial commit with RVC demo
Browse files- .gitattributes +1 -0
- added_IVF403_Flat_nprobe_1_yebama_v2.index +3 -0
- app.py +43 -0
- config.json +63 -0
- requirements.txt +5 -0
- response_1694593941525.json +38 -0
- response_1694594214307.json +36 -0
- yebama.zip +3 -0
- yebama_e200_s3200.pth +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
added_IVF403_Flat_nprobe_1_yebama_v2.index filter=lfs diff=lfs merge=lfs -text
|
added_IVF403_Flat_nprobe_1_yebama_v2.index
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0fb2e3b992e0d836b5e4976b660268ecd6bfb738f0f4fae239614d0264e805c
|
3 |
+
size 49714419
|
app.py
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import torch
|
3 |
+
import librosa
|
4 |
+
import numpy as np
|
5 |
+
from huggingface_hub import hf_hub_download
|
6 |
+
import zipfile
|
7 |
+
import os
|
8 |
+
|
9 |
+
# Descargar el modelo desde tu otra cuenta de Hugging Face
|
10 |
+
def load_model():
|
11 |
+
# Descargar archivos del modelo (ajusta los nombres según tu repositorio)
|
12 |
+
model_path = hf_hub_download(repo_id="gitgato/yebama", filename="yebama_e200_s3200.pth")
|
13 |
+
index_path = hf_hub_download(repo_id="gitgato/yebama", filename="IVF403_Flat_nprobe_1_yebama_v2.index")
|
14 |
+
config_path = hf_hub_download(repo_id="gitgato/yebama", filename="config.json")
|
15 |
+
|
16 |
+
# Aquí iría el código para cargar el modelo RVC (depende de tu implementación)
|
17 |
+
# Ejemplo simplificado:
|
18 |
+
# from rvc_inference import load_rvc_model
|
19 |
+
# model = load_rvc_model(model_path, config_path, index_path)
|
20 |
+
# return model
|
21 |
+
|
22 |
+
def process_audio(audio_file):
|
23 |
+
# Cargar el audio (ejemplo con librosa)
|
24 |
+
audio, sr = librosa.load(audio_file, sr=44100)
|
25 |
+
|
26 |
+
# Aquí iría la lógica de inferencia con RVC
|
27 |
+
# processed_audio = model.infer(audio)
|
28 |
+
|
29 |
+
# Simulando un resultado (reemplaza con tu modelo real)
|
30 |
+
processed_audio = audio # Esto es un placeholder
|
31 |
+
|
32 |
+
return sr, processed_audio
|
33 |
+
|
34 |
+
# Interfaz Gradio
|
35 |
+
iface = gr.Interface(
|
36 |
+
fn=process_audio,
|
37 |
+
inputs=gr.Audio(type="filepath", label="Sube tu audio"),
|
38 |
+
outputs=gr.Audio(label="Audio convertido"),
|
39 |
+
title="Demo de Yebama RVC",
|
40 |
+
description="Convierte tu voz con el modelo Yebama RVC."
|
41 |
+
)
|
42 |
+
|
43 |
+
iface.launch()
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"79": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"80": {
|
44 |
+
"content": "<ctc_blank>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"bos_token": "<s>",
|
53 |
+
"clean_up_tokenization_spaces": true,
|
54 |
+
"eos_token": "</s>",
|
55 |
+
"mask_token": "<mask>",
|
56 |
+
"model_max_length": 600,
|
57 |
+
"normalize": false,
|
58 |
+
"pad_token": "<pad>",
|
59 |
+
"processor_class": "SpeechT5Processor",
|
60 |
+
"sp_model_kwargs": {},
|
61 |
+
"tokenizer_class": "SpeechT5Tokenizer",
|
62 |
+
"unk_token": "<unk>"
|
63 |
+
}
|
requirements.txt
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
gradio>=3.0
|
2 |
+
torch>=1.10
|
3 |
+
librosa>=0.9.0
|
4 |
+
huggingface_hub
|
5 |
+
numpy
|
response_1694593941525.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"stability": 0.85,
|
3 |
+
"similarity_boost": 0.89,
|
4 |
+
"style": 0.18,
|
5 |
+
"use_speaker_boost": true
|
6 |
+
}
|
7 |
+
|
8 |
+
|
9 |
+
access-control-allow-headers: *
|
10 |
+
access-control-allow-methods: POST,OPTIONS,DELETE,GET
|
11 |
+
access-control-allow-origin: *
|
12 |
+
alt-svc: h3=":443"; ma=2592000,h3-29=":443"; ma=2592000 content-length: 80
|
13 |
+
content-type: application/json
|
14 |
+
date: Wed,13 Sep 2023 08:32:18 GMT
|
15 |
+
server: uvicorn
|
16 |
+
via: 1.1
|
17 |
+
google x-firefox-spdy: h2
|
18 |
+
|
19 |
+
|
20 |
+
{
|
21 |
+
"stability": 0,
|
22 |
+
"similarity_boost": 0,
|
23 |
+
"style": 0,
|
24 |
+
"use_speaker_boost": true
|
25 |
+
}
|
26 |
+
|
27 |
+
{
|
28 |
+
"detail": [
|
29 |
+
{
|
30 |
+
"loc": [
|
31 |
+
"string",
|
32 |
+
0
|
33 |
+
],
|
34 |
+
"msg": "string",
|
35 |
+
"type": "string"
|
36 |
+
}
|
37 |
+
]
|
38 |
+
}
|
response_1694594214307.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"stability": 0.93,
|
3 |
+
"similarity_boost": 0.96,
|
4 |
+
"style": 0.23,
|
5 |
+
"use_speaker_boost": true
|
6 |
+
}
|
7 |
+
|
8 |
+
access-control-allow-headers: *
|
9 |
+
access-control-allow-methods: POST,OPTIONS,DELETE,GET
|
10 |
+
access-control-allow-origin: *
|
11 |
+
alt-svc: h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
|
12 |
+
content-length: 80
|
13 |
+
content-type: application/json
|
14 |
+
date: Wed,13 Sep 2023 08:36:51
|
15 |
+
GMT server: uvicorn
|
16 |
+
via: 1.1 google x-firefox-spdy: h2
|
17 |
+
|
18 |
+
{
|
19 |
+
"stability": 0,
|
20 |
+
"similarity_boost": 0,
|
21 |
+
"style": 0,
|
22 |
+
"use_speaker_boost": true
|
23 |
+
}
|
24 |
+
|
25 |
+
{
|
26 |
+
"detail": [
|
27 |
+
{
|
28 |
+
"loc": [
|
29 |
+
"string",
|
30 |
+
0
|
31 |
+
],
|
32 |
+
"msg": "string",
|
33 |
+
"type": "string"
|
34 |
+
}
|
35 |
+
]
|
36 |
+
}
|
yebama.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdba5e3d3acd56cb7ddf5d6e3d6f0867c36cef5c5cac63c4d45e2b28791e1426
|
3 |
+
size 104943041
|
yebama_e200_s3200.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c280e247f5f3a05a2d0f2220248577215110ae0730d1ef7c290bff56e1a46d66
|
3 |
+
size 55228322
|