From 23d9f8a8bc0e58892058c102c2f06987f33643d7 Mon Sep 17 00:00:00 2001 From: Eren Golge Date: Fri, 16 Aug 2019 14:28:11 +0200 Subject: [PATCH] readme and config.json update --- README.md | 4 ++-- config.json | 12 ++++++------ 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 068c1762..39e507e1 100644 --- a/README.md +++ b/README.md @@ -10,9 +10,9 @@ TTS includes two different model implementations which are based on [Tacotron](h If you are new, you can also find [here](http://www.erogol.com/text-speech-deep-learning-architectures/) a brief post about TTS architectures and their comparisons. ## TTS Performance -

+

-[Details...](https://github.com/mozilla/TTS/issues/186) +[Details...](https://github.com/mozilla/TTS/wiki/Mean-Opinion-Score-Results) ## Requirements and Installation Highly recommended to use [miniconda](https://conda.io/miniconda.html) for easier installation. diff --git a/config.json b/config.json index 58e9b92b..2089c577 100644 --- a/config.json +++ b/config.json @@ -39,13 +39,13 @@ "warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr" "memory_size": -1, // ONLY TACOTRON - size of the memory queue used fro storing last decoder predictions for auto-regression. If < 0, memory queue is disabled and decoder only uses the last prediction frame. "attention_norm": "sigmoid", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron. - "prenet_type": "original", // ONLY TACOTRON2 - "original" or "bn". - "prenet_dropout": true, // ONLY TACOTRON2 - enable/disable dropout at prenet. + "prenet_type": "original", // "original" or "bn". + "prenet_dropout": true, // enable/disable dropout at prenet. "windowing": false, // Enables attention windowing. Used only in eval mode. - "use_forward_attn": false, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster. + "use_forward_attn": false, // if it uses forward attention. In general, it aligns faster. "forward_attn_mask": false, - "transition_agent": false, // ONLY TACOTRON2 - enable/disable transition agent of forward attention. - "location_attn": true, // ONLY TACOTRON2 - enable_disable location sensitive attention. It is enabled for TACOTRON by default. + "transition_agent": false, // enable/disable transition agent of forward attention. + "location_attn": true, // enable_disable location sensitive attention. It is enabled for TACOTRON by default. "loss_masking": true, // enable / disable loss masking against the sequence padding. "enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars. "stopnet": true, // Train stopnet predicting the end of synthesis. @@ -55,7 +55,7 @@ "batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'. "eval_batch_size":16, "r": 7, // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled. - "gradual_training": [[0, 7, 32], [10000, 5, 32], [50000, 3, 32], [130000, 2, 16], [290000, 1, 8]], // set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. + "gradual_training": [[0, 7, 32], [10000, 5, 32], [50000, 3, 32], [130000, 2, 16], [290000, 1, 8]], // ONLY TACOTRON - set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. "wd": 0.000001, // Weight decay weight. "checkpoint": true, // If true, it saves checkpoints per "save_step" "save_step": 10000, // Number of training steps expected to save traning stats and checkpoints.