【PaddleSpeech No.7-10】补全合成系列中的脚本中参数缺失 #4008
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…EAMDE.md修改：补充 stage 参数说明，明确 vocoder 选择逻辑
|
Thanks for your contribution! |
如果您看到了文档缺失的部分，可以提出来，我会把它继续新增到快乐开源任务中。 |
zxcd
reviewed
Mar 18, 2025
…update the READEM to be consistent with the script
zxcd
reviewed
Mar 19, 2025
examples/csmsc/tts2/run.sh
Outdated
| fi | ||
|
|
||
| if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then | ||
| # synthesize_e2e, vocoder is pwgan by default | ||
| CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 | ||
| # synthesize_e2e, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder |
examples/csmsc/tts3/README_cn.md
Outdated
| ``` | ||
| `--stage` 用于合成过程中控制声码器模型，可取值为 `0` 或 `1`，分别对应使用 `pwgan` 或 `hifigan` 模型作为声码器。 |
There was a problem hiding this comment.
same with above. pls check all files.
examples/csmsc/tts0/README.md
Outdated
| ``` | ||
| `--stage` controls the vocoder model during synthesis, which can be `0` or `1` or `2` or `3`, use `pwgan` or `multi band melgan` or `style melgan` or `hifigan`model as vocoder. |
There was a problem hiding this comment.
why don't use dict to present this message?
such as use stage 0-4 to select the vocoder to use {pwgan, multi band melgan, ....}
This kind of expression is a bit cumbersome now.
There was a problem hiding this comment.
OK, I checked the README and sh files in the four folders under csmsc and believe there should be no issues.
zxcd
reviewed
Mar 24, 2025
examples/csmsc/tts3_rhy/README.md
Outdated
| 1. **source path**. | ||
| 2. preprocess the dataset. | ||
| 3. train the model. | ||
| 4. synthesize wavs. | ||
| - synthesize waveform from `metadata.jsonl`. | ||
| - use stage `1,3,4` to select the vocoder to use {`multi band melgan`, `hifigan`, `wavernn`} |
There was a problem hiding this comment.
add the usage of synthesize.sh and synthesize_e2e.sh like other files.
| @@ -14,11 +14,13 @@ Remember in our repo, you should add `--rhy-with-duration` flag to obtain the rh | |||
| Assume the path to the dataset is `~/datasets/BZNSYP`. | |||
| Assume the path to the MFA result of CSMSC is `./baker_alignment_tone`. | |||
| Run the command below to | |||
|
|
|||
There was a problem hiding this comment.
also change ths file add stage information?
examples/csmsc/tts3_rhy/run.sh
Outdated
| @@ -28,11 +28,12 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then | |||
| fi | |||
|
|
|||
| if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then | |||
| # synthesize, vocoder is pwgan by default | |||
| CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 | |||
| # synthesize, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder | |||
examples/csmsc/tts3/README_cn.md
Outdated
| ``` | ||
| `--stage` 用于合成过程中控制声码器模型，可取值为 `0` 或 `1`，分别对应使用 `pwgan` 或 `hifigan` 模型作为声码器。 |
|
This PR has too much content and is a bit messy, so close |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR types
Function optimization, Docs
PR changes
Docs, Others
Describe
本次修改主要包含：
对 examples/csmsc/ 文件夹下的
tts0、tts2、tts3；以及examples/csmsc/tts3_rhy/ 下的READEME.md文档和run.sh脚本均进行修改。其中，在修改过程中发现tts3下还有README_cn.md文档，也对其同时进行修改。脚本优化： 为 run.sh 中的合成阶段添加 --stage 参数，根据对应的sh下文件的合成阶段进行stage添加
文档完善： 在 README.md 中补充 stage 参数说明，明确 vocoder 选择逻辑，优化文档措辞，如将
0 or 1 or 2 or 3 ...改为0-4。Issue链接：#3997
@luotao1 @zxcd