diff --git a/config_cluster.json b/config_cluster.json index e651fe2..4816764 100644 --- a/config_cluster.json +++ b/config_cluster.json @@ -1,6 +1,6 @@ { "run_name": "mozilla-fattn-agent-masking", - "run_description": "Original prenet,fattn and fattn agent with loss masking.", + "run_description": "finetune 4706 with prenet BN. Loss masking, fattn.", "audio":{ // Audio processing parameters @@ -42,8 +42,8 @@ "attention_norm": "softmax", // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron. "prenet_type": "original", // ONLY TACOTRON2 - "original" or "bn". "use_forward_attn": true, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster. - "transition_agent": true, // ONLY TACOTRON2 - enable/disable transition agent of forward attention. - "location_attn": false, // ONLY TACOTRON2 - enable_disable location sensitive attention. It is enabled for TACOTRON by default. + "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. "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. @@ -66,7 +66,7 @@ "min_seq_len": 0, // DATASET-RELATED: minimum text length to use in training "max_seq_len": 150, // DATASET-RELATED: maximum text length "output_path": "../keep/", // DATASET-RELATED: output path for all training outputs. - "num_loader_workers": 8, // number of training data loader processes. Don't set it too big. 4-8 are good values. + "num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values. "num_val_loader_workers": 4, // number of evaluation data loader processes. "phoneme_cache_path": "mozilla_us_phonemes", // phoneme computation is slow, therefore, it caches results in the given folder. "use_phonemes": true, // use phonemes instead of raw characters. It is suggested for better pronounciation.