Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
sambert-hifigan_pytorch
Commits
56613154
Commit
56613154
authored
Mar 02, 2024
by
liugh5
Browse files
Update README.md
parent
007b3c1b
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
7 additions
and
0 deletions
+7
-0
README.md
README.md
+7
-0
No files found.
README.md
View file @
56613154
...
@@ -111,6 +111,8 @@ bash feats_extract.sh
...
@@ -111,6 +111,8 @@ bash feats_extract.sh
#### 单卡训练
#### 单卡训练
```
```
# 微调声学模型是配置驱动的,我们使用预训练模型中的speech_personal_sambert-hifigan_nsf_tts_zh-cn_pretrain_16k/basemodel_16k/sambert/config.yaml作为训练配置文件。 我们提供默认的PTTS 默认使用的finetune参数值,希望在basemodel的基础上继续微调 一定步数 并保存,即我们修改train_max_steps配置项。
# 完成配置项修改后,我们就可以使用以下命令训练声学模型了:
HIP_VISIBLE_DEVICES=0 python3 kantts/bin/train_sambert.py \
HIP_VISIBLE_DEVICES=0 python3 kantts/bin/train_sambert.py \
--model_config speech_personal_sambert-hifigan_nsf_tts_zh-cn_pretrain_16k/basemodel_16k/sambert/config.yaml \
--model_config speech_personal_sambert-hifigan_nsf_tts_zh-cn_pretrain_16k/basemodel_16k/sambert/config.yaml \
--root_dir training_stage/ptts_feats \
--root_dir training_stage/ptts_feats \
...
@@ -132,8 +134,13 @@ HIP_VISIBLE_DEVICES=0 python3 kantts/bin/text_to_wav.py \
...
@@ -132,8 +134,13 @@ HIP_VISIBLE_DEVICES=0 python3 kantts/bin/text_to_wav.py \
## result
## result
可在输出文件夹res/ptts_syn下找到克隆的语音文件。
可在输出文件夹res/ptts_syn下找到克隆的语音文件。
## 精度
训练使用的加速卡:Z100
## 应用场景
## 应用场景
### 算法分类
### 算法分类
语音处理
语音处理
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment