-
Hi @adelacvg
Can we use this kind model for speech to speech (Voice conversion).
-
# Trending repositories for C#
1. [**davidfowl / AspNetCoreDiagnosticScenarios**](https://github.com/davidfowl/AspNetCoreDiagnosticScenarios)
__This repository has examples of bro…
-
## Contents
@Hiroshiba
According to #498 , it might be the time to take English into consideration.
I suggest we start with the corpus [LJSpeech](https://keithito.com/LJ-Speech-Dataset/), si…
-
In Zero Shot mode,if the Prompt text or Target text does not end with punctuation (eg '.' or '?' or '!' ), the following error message will happen:
Traceback (most recent call last):
File "./tes…
-
我用libritts训练了模型,看loss像是收敛了
下面是我用LJSpeech的数据进行推理的结果:
https://drive.google.com/drive/folders/1_mkx0ze_Y0P1uX3kCjAWu3rgHGhyUQeP?usp=sharing
我有两个疑问:
1. 和你给出来的用LJSpeech训练推理出的效果相比,我合成的*-full.wav前面的效果怎…
-
-
have you seen this dataset? maybe it's better suited for zero-shot task, more natural speech than audiobook
https://github.com/open-mmlab/Amphion/blob/main/preprocessors/Emilia/README.md
-
看运行只有CosyVoice-300M基础模型,下面client使用能分别使用sft|zero_shot|cross_lingual|instruct 4中模型?我看前面文档有写CosyVoice-300M-sft是tts,CosyVoice-300M直接是克隆,CosyVoice-300M-instruct 是加入语态控制
docker run -d --runtime=nvidia -p 5…
-
run inference code as shown below:
```
ref_path="female01.wav"
cosyvoice = CosyVoice("pretrained_models/CosyVoice-300M")
# zero_shot usage
prompt_speech_16k = load_wav(ref_path, 16000)
output…
-
当我按照readme中步骤安装了环境下载了模型然后运行export PYTHONPATH=third_party/AcademiCodec:third_party/Matcha-TTS和from cosyvoice.cli.cosyvoice import CosyVoice
from cosyvoice.utils.file_utils import load_wav
import torc…