From 6077fa59d9c95aec3c86ab6e96ee8f84ccecc085 Mon Sep 17 00:00:00 2001 From: nyx-c-language Date: Wed, 19 Mar 2025 00:42:12 +0800 Subject: [PATCH] update csmsc/tts3_rhy --- examples/csmsc/tts3_rhy/README.md | 2 +- examples/csmsc/tts3_rhy/run.sh | 5 ++++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/examples/csmsc/tts3_rhy/README.md b/examples/csmsc/tts3_rhy/README.md index a0e5732b4..9ab783deb 100644 --- a/examples/csmsc/tts3_rhy/README.md +++ b/examples/csmsc/tts3_rhy/README.md @@ -20,7 +20,7 @@ Run the command below to 3. train the model. 4. synthesize wavs. - synthesize waveform from `metadata.jsonl`. - - select vocoder type via `--stage` (0 = pwgan, 1 = hifigan) + - select vocoder type via `--stage` (0 = pwgan, 1 = multi band melgan, 3 = hifigan, 4 = wavernn) - synthesize waveform from a text file. 5. inference using the static model. ```bash diff --git a/examples/csmsc/tts3_rhy/run.sh b/examples/csmsc/tts3_rhy/run.sh index 61020093b..765985304 100755 --- a/examples/csmsc/tts3_rhy/run.sh +++ b/examples/csmsc/tts3_rhy/run.sh @@ -33,6 +33,9 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then fi if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then - # synthesize_e2e, vocoder is pwgan by default stage 0, stage 1 will use hifigan as vocoder + # synthesize_e2e, vocoder is pwgan by default stage 0 + # stage 1 will use multi band melgan as vocoder + # stage 3 will use hifigan as vocoder + # stage 4 will use wavernn as vocoder CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh --stage 0 ${conf_path} ${train_output_path} ${ckpt_name} || exit -1 fi