diff --git a/.compute b/.compute index 47d3419d..c1957615 100644 --- a/.compute +++ b/.compute @@ -4,4 +4,4 @@ pip3 install https://download.pytorch.org/whl/cu100/torch-1.0.1.post2-cp36-cp36m yes | apt-get install espeak python3 setup.py develop # python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ --restore_path ${USER_DIR}/best_model.pth.tar -python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ \ No newline at end of file +python3 train.py --config_path config.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ \ No newline at end of file diff --git a/config.json b/config.json index 037f8249..d07ea7d0 100644 --- a/config.json +++ b/config.json @@ -42,7 +42,7 @@ "batch_size": 32, // Batch size for training. Lower values than 32 might cause hard to learn attention. "eval_batch_size":32, "r": 5, // Number of frames to predict for step. - "wd": 0.00001, // Weight decay weight. + "wd": 0.000001, // Weight decay weight. "checkpoint": true, // If true, it saves checkpoints per "save_step" "save_step": 5000, // Number of training steps expected to save traning stats and checkpoints. "print_step": 50, // Number of steps to log traning on console. diff --git a/config_cluster.json b/config_cluster.json index efe53c8a..073923be 100644 --- a/config_cluster.json +++ b/config_cluster.json @@ -1,6 +1,6 @@ { "model_name": "tts-master", - "model_description": "tts master cluster test", + "model_description": "tts master with symbols update", "audio":{ "audio_processor": "audio", // to use dictate different audio processors, if available. @@ -25,6 +25,11 @@ "do_trim_silence": true // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true) }, + "distributed":{ + "backend": "nccl", + "url": "tcp:\/\/localhost:54321" + }, + "embedding_size": 256, // Character embedding vector length. You don't need to change it in general. "text_cleaner": "phoneme_cleaners", "epochs": 1000, // total number of epochs to train. @@ -46,9 +51,9 @@ "run_eval": true, "data_path": "/media/erogol/data_ssd/Data/LJSpeech-1.1", // DATASET-RELATED: can overwritten from command argument - "meta_file_train": "prompts_train.data", // DATASET-RELATED: metafile for training dataloader. - "meta_file_val": "prompts_val.data", // DATASET-RELATED: metafile for evaluation dataloader. - "dataset": "nancy", // DATASET-RELATED: one of TTS.dataset.preprocessors depending on your target dataset. Use "tts_cache" for pre-computed dataset by extract_features.py + "meta_file_train": "metadata_train.csv", // DATASET-RELATED: metafile for training dataloader. + "meta_file_val": "metadata_val.csv", // DATASET-RELATED: metafile for evaluation dataloader. + "dataset": "ljspeech", // DATASET-RELATED: one of TTS.dataset.preprocessors depending on your target dataset. Use "tts_cache" for pre-computed dataset by extract_features.py "min_seq_len": 0, // DATASET-RELATED: minimum text length to use in training "max_seq_len": 300, // DATASET-RELATED: maximum text length "output_path": "models/", // DATASET-RELATED: output path for all training outputs.