upload files

README.md

@@ -6,7 +6,7 @@ Welcome to play around with the base model, a Trilingual Anime VITS!
 [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer)
 
 ### Currently Supported Tasks:
-- [x] Convert user's voice to characters listed below
+- [x] Convert user's voice to characters listed [here](https://github.com/SongtingLiu/VITS_voice_conversion/blob/main/configs/finetune_speaker.json)
 - [x] Chinese, English, Japanese TTS with user's voice
 - [ ] Chinese, English, Japanese TTS with custom characters...
 
@@ -30,6 +30,10 @@ because the original VITS has some dependencies that are difficult to configure.
 
 ## Inference or Usage
 
-1. Clone this repo
-2. Install dependencies
-3. run VC_inference.py
+1. Install Python if you haven't done so (Python >= 3.7)
+2. Clone this repo:  
+`git clone https://github.com/SongtingLiu/VITS_voice_conversion.git`
+3. Install dependencies  
+`pip install -r requirements.txt`
+4. run VC_inference.py  
+`python VC_inference.py`

VC_inference.py

@@ -1,26 +1,15 @@
 import os
-import json
-import math
 import numpy as np
 import torch
 from torch import no_grad, LongTensor
 import librosa
-from torch.nn import functional as F
 import argparse
 from mel_processing import spectrogram_torch
-import commons
 import utils
 from models_infer import SynthesizerTrn
-from text import text_to_sequence
 import gradio as gr
 import torchaudio
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
-def get_text(text, hps):
-    text_norm = text_to_sequence(text, hps.symbols, hps.data.text_cleaners)
-    if hps.data.add_blank:
-        text_norm = commons.intersperse(text_norm, 0)
-    text_norm = torch.LongTensor(text_norm)
-    return text_norm
 
 def create_vc_fn(model, hps, speaker_ids):
     def vc_fn(original_speaker, target_speaker, record_audio, upload_audio, denoise):

requirements_infer.txt

@@ -0,0 +1,11 @@
+Cython
+librosa
+numpy
+scipy
+torch
+torchvision
+torchaudio
+unidecode
+protobuf
+demucs
+gradio