From 052e466a2cf2a97889dafca0b1e34bf04ce87caa Mon Sep 17 00:00:00 2001 From: enkilee Date: Mon, 3 Mar 2025 11:53:00 +0800 Subject: [PATCH] fix --- examples/aishell3/tts3/README.md | 6 ++++-- examples/aishell3/tts3/run.sh | 8 ++++---- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/examples/aishell3/tts3/README.md b/examples/aishell3/tts3/README.md index f97a84b50..8f3f66dac 100644 --- a/examples/aishell3/tts3/README.md +++ b/examples/aishell3/tts3/README.md @@ -109,8 +109,9 @@ pwg_aishell3_ckpt_0.5 ``` `./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`. ```bash -CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} +CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} ``` +`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder. ```text usage: synthesize.py [-h] [--am {speedyspeech_csmsc,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech,tacotron2_aishell3}] @@ -157,8 +158,9 @@ optional arguments: ``` `./local/synthesize_e2e.sh` calls `${BIN_DIR}/../synthesize_e2e.py`, which can synthesize waveform from text file. ```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` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder. ```text usage: synthesize_e2e.py [-h] [--am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech}] diff --git a/examples/aishell3/tts3/run.sh b/examples/aishell3/tts3/run.sh index 8dcecaa03..3fd5d73c6 100755 --- a/examples/aishell3/tts3/run.sh +++ b/examples/aishell3/tts3/run.sh @@ -27,13 +27,13 @@ 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} ${ckpt_name} || exit -1 + # synthesize, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder + CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 fi if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then - # synthesize_e2e, vocoder is pwgan by default - CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 + # synthesize_e2e, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder + CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 fi if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then