mirror of
https://github.com/babysor/MockingBird.git
synced 2024-03-22 13:11:31 +08:00
Fix nits of file path
This commit is contained in:
parent
c5d03fb3cb
commit
c00474525a
|
@ -105,7 +105,7 @@
|
|||
### 4. 番外:语音转换Voice Conversion(PPG based)
|
||||
想像柯南拿着变声器然后发出毛利小五郎的声音吗?本项目现基于PPG-VC,引入额外两个模块(PPG extractor + PPG2Mel), 可以实现变声功能。(文档不全,尤其是训练部分,正在努力补充中)
|
||||
#### 4.0 准备环境
|
||||
* 确保项目以上环境已经安装ok,运行`pip install -r requirements_vc.txt` 来安装剩余的必要包。
|
||||
* 确保项目以上环境已经安装ok,运行`pip install espnet` 来安装剩余的必要包。
|
||||
* 下载以下模型 链接:https://pan.baidu.com/s/1bl_x_DHJSAUyN2fma-Q_Wg
|
||||
提取码:gh41
|
||||
* 24K采样率专用的vocoder(hifigan)到 *vocoder\saved_models\xxx*
|
||||
|
|
|
@ -19,8 +19,8 @@ AUDIO_SAMPLES_DIR = 'samples\\'
|
|||
SYN_MODELS_DIRT = "synthesizer\\saved_models"
|
||||
ENC_MODELS_DIRT = "encoder\\saved_models"
|
||||
VOC_MODELS_DIRT = "vocoder\\saved_models"
|
||||
TEMP_SOURCE_AUDIO = "wavs/temp_source.wav"
|
||||
TEMP_RESULT_AUDIO = "wavs/temp_result.wav"
|
||||
TEMP_SOURCE_AUDIO = "wavs\\temp_source.wav"
|
||||
TEMP_RESULT_AUDIO = "wavs\\temp_result.wav"
|
||||
|
||||
# Load local sample audio as options TODO: load dataset
|
||||
if os.path.isdir(AUDIO_SAMPLES_DIR):
|
||||
|
|
Loading…
Reference in New Issue
Block a user