You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
# synthesize, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
fi
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
# synthesize_e2e, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
fi
在 README.md 中修改:
`./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`.
CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name}
`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder.
任务三修改示例
修改examples/csmsc/voc3/README.md
HiFiGAN checkpoint contains files listed below.
mb_melgan_csmsc_ckpt_0.1.1
├── default.yaml # default config used to train MultiBand MelGAN
├── feats_stats.npy # statistics used to normalize spectrogram when training MultiBand MelGAN
└── snapshot_iter_1000000.pdz # generator parameters of MultiBand MelGAN
📣PaddleSpeech 快乐开源活动
旨在鼓励更多的开发者参与到飞桨大模型套件的开源建设中,帮助社区修复 bug 或贡献 feature,共建飞桨。
任务目标
目前由于版本问题,文档已经跟不上代码啦!
任务一:修正合成vocoder中的synthesize_e2e.sh中参数错误
任务二:补全合成系列中的脚本中参数缺失
examples/aishell3/tts3/README.md
examples/aishell3_vctk/ernie_sat/README.md
examples/canton/tts3/README.md
examples/csmsc/tts0/README.md
examples/csmsc/tts2/README.md
examples/csmsc/tts3/README.md
examples/csmsc/tts3_rhy/README.md
examples/ljspeech/tts3/README.md
examples/opencpop/svs1/README.md
examples/vctk/ernie_sat/README.md
examples/vctk/tts3/README.md
任务三:修正文本书写错误(随时更新)
任务一修改示例
修正目标:
examples/*/voc*/local/synthesize_e2e.sh
例如:examples/csmsc/voc1/local/synthesize_e2e.sh
由于合成时训练的是 voc 而非 am, 因此包含
train_output_path
的应该是 --voc, --voc_config 等 voc 相关部分,--am 相关部分按照examples/csmsc/voc1/README.md
中的描述修改为fastspeech2_nosil_baker_ckpt_0.4
文件夹下的相关文件。任务二修改示例
修正目标:
examples/*/*/local/run.sh
,examples/*/*/README.md
在部分
synthesize_e2e.sh
和synthesize.sh
中,通过对 stage 的修改支持多种模型的推理,但该参数未在对应的run.sh
和README.md
中暴露,需要将参数和对应的说明添加补充全。例如 :
examples/aishell3/tts3/local/synthesize_e2e.sh
中通过 stage 控制分别使用 pwgan,hifigan 进行推理。run.sh
中修改:README.md
中修改:任务三修改示例
修改
examples/csmsc/voc3/README.md
该
README.md
中模型下载 MultiBand MelGAN 模型,但文件列表写的是 HiFiGAN 。看板信息
统计信息
The text was updated successfully, but these errors were encountered: