From 65638f9517861a9ccf15f2d96649ac79568b8b76 Mon Sep 17 00:00:00 2001 From: rich04lin <152049331+rich04lin@users.noreply.github.com> Date: Wed, 19 Mar 2025 17:52:54 +0800 Subject: [PATCH] num5 --- examples/csmsc/tts0/README.md | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/examples/csmsc/tts0/README.md b/examples/csmsc/tts0/README.md index 9aa46cc87..2f11049cf 100644 --- a/examples/csmsc/tts0/README.md +++ b/examples/csmsc/tts0/README.md @@ -18,6 +18,7 @@ Run the command below to 3. train the model. 4. synthesize wavs. - synthesize waveform from `metadata.jsonl`. + - `--stage` controls the vocoder model during synthesis (0 = pwgan, 1 = hifigan). - synthesize waveform from a text file. ```bash @@ -99,9 +100,8 @@ pwg_baker_ckpt_0.4 ``` `./local/synthesize.sh` calls `${BIN_DIR}/../synthesize.py`, which can synthesize waveform from `metadata.jsonl`. ```bash -CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} +CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} ``` -`--stage` controls the vocoder model during synthesis, which can be `0` or `1`, use `pwgan` or `hifigan` model as vocoder. ```text usage: synthesize.py [-h] [--am {speedyspeech_csmsc,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech,tacotron2_aishell3}] @@ -148,9 +148,8 @@ optional arguments: ``` `./local/synthesize_e2e.sh` calls `${BIN_DIR}/../synthesize_e2e.py`, which can synthesize waveform from text file. ```bash -CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} +CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${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}]