OpenVoice克隆声音

git地址 https://github.com/myshell-ai/OpenVoice

安装

conda create -n openvoice python=3.9
conda activate openvoice
git clone git@github.com:myshell-ai/OpenVoice.git
cd OpenVoice
pip install -e .

checkpoints下载

https://myshell-public-repo-hosting.s3.amazonaws.com/openvoice/checkpoints_v2_0417.zip

v1版本

import os
import torch
from openvoice import se_extractor
from openvoice.api import BaseSpeakerTTS, ToneColorConverter

ckpt_base = 'checkpoints/base_speakers/EN'
ckpt_converter = 'checkpoints/converter'
device="cuda:0" if torch.cuda.is_available() else "cpu"
output_dir = 'outputs'

base_speaker_tts = BaseSpeakerTTS(f'{ckpt_base}/config.json', device=device)
base_speaker_tts.load_ckpt(f'{ckpt_base}/checkpoint.pth')

tone_color_converter = ToneColorConverter(f'{ckpt_converter}/config.json', device=device)
tone_color_converter.load_ckpt(f'{ckpt_converter}/checkpoint.pth')

os.makedirs(output_dir, exist_ok=True)

source_se = torch.load(f'{ckpt_base}/en_default_se.pth').to(device)

#需要克隆的声音
reference_speaker = 'resources/example_reference.mp3'
target_se, audio_name = se_extractor.get_se(reference_speaker, tone_color_converter, target_dir='processed', vad=True)
# 克隆后的输出
save_path = f'{output_dir}/output_en_default.wav'

# 要生成的语句
text = "This audio is generated by OpenVoice."
src_path = f'{output_dir}/tmp.wav'
## 尝试不同风格
# 可选: friendly, cheerful, excited, sad, angry, terrified, shouting, whispering.
# 语速 speed 0.9.
base_speaker_tts.tts(text, src_path, speaker='default', language='English', speed=1.0)

# 执行
encode_message = "@MyShell"
tone_color_converter.convert(
    audio_src_path=src_path,
    src_se=source_se,
    tgt_se=target_se,
    output_path=save_path,
    message=encode_message)

中文

#中文
ckpt_base = 'checkpoints/base_speakers/ZH'
base_speaker_tts = BaseSpeakerTTS(f'{ckpt_base}/config.json', device=device)
base_speaker_tts.load_ckpt(f'{ckpt_base}/checkpoint.pth')

source_se = torch.load(f'{ckpt_base}/zh_default_se.pth').to(device)
save_path = f'{output_dir}/output_chinese.wav'
text = "今天天气真好，我们一起出去吃饭吧。"
src_path = f'{output_dir}/tmp.wav'
base_speaker_tts.tts(text, src_path, speaker='default', language='Chinese', speed=1.0)

# 开始
encode_message = "@MyShell"
tone_color_converter.convert(
    audio_src_path=src_path,
    src_se=source_se,
    tgt_se=target_se,
    output_path=save_path,
    message=encode_message)