From a34076af3587ddc2de1c82a73230f6bdfb859a49 Mon Sep 17 00:00:00 2001 From: Arvind Suresh Date: Tue, 3 May 2022 08:01:10 -0400 Subject: [PATCH] Update documentation for multi-gpu training --- docs/source/faq.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/docs/source/faq.md b/docs/source/faq.md index 3de6663d8b..2157082cf1 100644 --- a/docs/source/faq.md +++ b/docs/source/faq.md @@ -59,8 +59,7 @@ We tried to collect common issues and questions we receive about 🐸TTS. It is 6. Train your model. - SingleGPU training: ```CUDA_VISIBLE_DEVICES="0" python train_tts.py --config_path config.json``` - - MultiGPU training: ```CUDA_VISIBLE_DEVICES="0,1,2" python distribute.py --script train_tts.py --config_path config.json``` - - This command uses all the GPUs given in ```CUDA_VISIBLE_DEVICES```. If you don't specify, it uses all the GPUs available. + - MultiGPU training: ```python3 -m trainer.distribute --gpus "0,1" --script TTS/bin/train_tts.py --config_path config.json``` **Note:** You can also train your model using pure 🐍 python. Check ```{eval-rst} :ref: 'tutorial_for_nervous_beginners'```. @@ -111,4 +110,4 @@ The best approach is to pick a set of promising models and run a Mean-Opinion-Sc ## My Tacotron model does not stop - I see "Decoder stopped with 'max_decoder_steps" - Stopnet does not work. - In general, all of the above relates to the `stopnet`. It is the part of the model telling the `decoder` when to stop. - In general, a poor `stopnet` relates to something else that is broken in your model or dataset. Especially the attention module. -- One common reason is the silent parts in the audio clips at the beginning and the ending. Check ```trim_db``` value in the config. You can find a better value for your dataset by using ```CheckSpectrogram``` notebook. If this value is too small, too much of the audio will be trimmed. If too big, then too much silence will remain. Both will curtail the `stopnet` performance. \ No newline at end of file +- One common reason is the silent parts in the audio clips at the beginning and the ending. Check ```trim_db``` value in the config. You can find a better value for your dataset by using ```CheckSpectrogram``` notebook. If this value is too small, too much of the audio will be trimmed. If too big, then too much silence will remain. Both will curtail the `stopnet` performance.