From bdcd3062225f760baa3ed964087116dd6685920f Mon Sep 17 00:00:00 2001 From: Eren Golge Date: Tue, 14 May 2019 22:35:04 +0200 Subject: [PATCH] config updates --- config_cluster.json | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/config_cluster.json b/config_cluster.json index 1a9ec91f..0224e204 100644 --- a/config_cluster.json +++ b/config_cluster.json @@ -1,6 +1,6 @@ { - "run_name": "mozilla-no-loc-fattn-stopnet", - "run_description": "using forward attention, with original prenet, merged stopnet. Compare this with ", + "run_name": "mozilla-no-loc-fattn-stopnet-sigmoid", + "run_description": "using forward attention, with original prenet, merged stopnet, sigmoid. Compare this with 4780 ", "audio":{ // Audio processing parameters @@ -39,7 +39,7 @@ "warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr" "windowing": false, // Enables attention windowing. Used only in eval mode. "memory_size": 5, // ONLY TACOTRON - memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5. - "attention_norm": "softmax", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron. + "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. "use_forward_attn": true, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster. @@ -47,9 +47,10 @@ "location_attn": false, // ONLY TACOTRON2 - enable_disable location sensitive attention. It is enabled for TACOTRON by default. "loss_masking": false, // 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. + "stopnet": false, // Train stopnet predicting the end of synthesis. "separate_stopnet": false, // Train stopnet seperately if 'stopnet==true'. It prevents stopnet loss to influence the rest of the model. It causes a better model, but it trains SLOWER. - + "tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. + "batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention. "eval_batch_size":16, "r": 1, // Number of frames to predict for step. @@ -57,7 +58,6 @@ "checkpoint": true, // If true, it saves checkpoints per "save_step" "save_step": 1000, // Number of training steps expected to save traning stats and checkpoints. "print_step": 10, // Number of steps to log traning on console. - "tb_model_param_stats": true, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. "batch_group_size": 0, //Number of batches to shuffle after bucketing. "run_eval": true,