fix the errors 2025/3/24

pull/4008/head
nyx-c-language 6 months ago
parent e46a165314
commit bef985c6fc

@ -115,7 +115,7 @@ pwg_baker_ckpt_0.4
```bash ```bash
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
``` ```
`--stage` 用于合成过程中控制声码器模型,可取值为 `0``1`,分别对应使用 `pwgan``hifigan` 模型作为声码器 `--stage` 参数用于控制合成过程中使用的声码器模型。通过设置 `0-4` 阶段值,可以选择以下声码器之一:`pwgan`、`multi band melgan`、`style melgan`、`hifigan` 或 `wavernn`
```text ```text
usage: synthesize.py [-h] usage: synthesize.py [-h]
@ -164,8 +164,12 @@ optional arguments:
`./local/synthesize_e2e.sh` 调用 `${BIN_DIR}/../synthesize_e2e.py`,即可从文本文件中合成波形。 `./local/synthesize_e2e.sh` 调用 `${BIN_DIR}/../synthesize_e2e.py`,即可从文本文件中合成波形。
```bash ```bash
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
``` ```
`--stage` 参数用于控制合成过程中使用的声码器模型。通过设置阶段值 `0、1、3、4`,可以选择以下声码器之一:`pwgan`、`multi band melgan`、`hifigan` 或 `wavernn`
```text ```text
usage: synthesize_e2e.py [-h] usage: synthesize_e2e.py [-h]
[--am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech}] [--am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech}]

@ -20,7 +20,6 @@ Run the command below to
3. train the model. 3. train the model.
4. synthesize wavs. 4. synthesize wavs.
- synthesize waveform from `metadata.jsonl`. - synthesize waveform from `metadata.jsonl`.
- use stage `1,3,4` to select the vocoder to use {`multi band melgan`, `hifigan`, `wavernn`}
- synthesize waveform from a text file. - synthesize waveform from a text file.
5. inference using the static model. 5. inference using the static model.
```bash ```bash

@ -28,7 +28,8 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
fi fi
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
# synthesize, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder # synthesize, vocoder is pwgan by default stage 0
# use stage 1-4 to select the vocoder to use {multi band melgan, style melgan, hifigan, wavernn}
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
fi fi

Loading…
Cancel
Save