Hugging Face's logo

myshell-ai
/
DreamVoice

English
myshell
speech-to-speech
Model card Files
xet
Community
2
Higobeatz commited on
Commit
9545c20
·
1 Parent(s): 094a0e1

openvoice plugin

Browse files
Files changed (2) hide show
  1. .ipynb_checkpoints/README-checkpoint.md +3 -2
  2. README.md +3 -2
.ipynb_checkpoints/README-checkpoint.md CHANGED
@@ -94,11 +94,12 @@ dreamvoice.save_audio('gen2.wav', gen_audio2, sr)
94
  # Training Guide
95
 
96
  1. download VCTK and LibriTTS-R
97
- 2. extract speaker embeddings and cache in local path:
 
98
  ```
99
  python dreamvoice/train_utils/prepare/prepare_se.py
100
  ```
101
- 3. modify trainning config and train your dreamvoice plugin:
102
  ```
103
  cd dreamvoice/train_utils/src
104
  accelerate launch train.py
 
94
  # Training Guide
95
 
96
  1. download VCTK and LibriTTS-R
97
+ 2. download DreamVoice DataSet
98
+ 3. extract speaker embeddings and cache in local path:
99
  ```
100
  python dreamvoice/train_utils/prepare/prepare_se.py
101
  ```
102
+ 4. modify trainning config and train your dreamvoice plugin:
103
  ```
104
  cd dreamvoice/train_utils/src
105
  accelerate launch train.py
README.md CHANGED
@@ -94,11 +94,12 @@ dreamvoice.save_audio('gen2.wav', gen_audio2, sr)
94
  # Training Guide
95
 
96
  1. download VCTK and LibriTTS-R
97
- 2. extract speaker embeddings and cache in local path:
 
98
  ```
99
  python dreamvoice/train_utils/prepare/prepare_se.py
100
  ```
101
- 3. modify trainning config and train your dreamvoice plugin:
102
  ```
103
  cd dreamvoice/train_utils/src
104
  accelerate launch train.py
 
94
  # Training Guide
95
 
96
  1. download VCTK and LibriTTS-R
97
+ 2. download DreamVoice DataSet
98
+ 3. extract speaker embeddings and cache in local path:
99
  ```
100
  python dreamvoice/train_utils/prepare/prepare_se.py
101
  ```
102
+ 4. modify trainning config and train your dreamvoice plugin:
103
  ```
104
  cd dreamvoice/train_utils/src
105
  accelerate launch train.py