diff --git a/.compute b/.compute index 358722b6..fe1c69c7 100644 --- a/.compute +++ b/.compute @@ -5,10 +5,10 @@ yes | apt-get install espeak yes | apt-get install tmux yes | apt-get install zsh pip3 install https://download.pytorch.org/whl/cu100/torch-1.0.1.post2-cp36-cp36m-linux_x86_64.whl -wget https://www.dropbox.com/s/rowimjoosnmdgj4/best_model_4702.pth.tar?dl=0 -O best_model_4702.pth.tar +# wget https://www.dropbox.com/s/m8waow6b3ydpf6h/MozillaDataset.tar.gz?dl=0 -O /data/rw/home/mozilla.tar wget https://www.dropbox.com/s/wqn5v3wkktw9lmo/install.sh?dl=0 -O install.sh sudo sh install.sh python3 setup.py develop -# python3 distribute.py --config_path config_cluster.json --data_path ${USER_DIR}/Mozilla/ --restore_path ${USER_DIR}/best_model_4700.pth.tar +python3 distribute.py --config_path config_cluster.json --data_path ${USER_DIR}/MozillaAll/Mozilla/ --restore_path ${USER_DIR}/checkpoint_123000_4761.pth.tar # python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/mozilla/Judy/ -while true; do sleep 1000000; done +# while true; do sleep 1000000; done diff --git a/config_cluster.json b/config_cluster.json index 48167649..9b68e40c 100644 --- a/config_cluster.json +++ b/config_cluster.json @@ -1,6 +1,6 @@ { - "run_name": "mozilla-fattn-agent-masking", - "run_description": "finetune 4706 with prenet BN. Loss masking, fattn.", + "run_name": "mozilla-fattn-stopnet", + "run_description": "Finetune 4761 with BN", "audio":{ // Audio processing parameters @@ -40,14 +40,14 @@ "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. - "prenet_type": "original", // ONLY TACOTRON2 - "original" or "bn". + "prenet_type": "bn", // ONLY TACOTRON2 - "original" or "bn". "use_forward_attn": true, // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster. "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. + "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. - "batch_size": 24, // Batch size for training. Lower values than 32 might cause hard to learn attention. + "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. "wd": 0.000001, // Weight decay weight. @@ -60,12 +60,12 @@ "run_eval": true, "test_delay_epochs": 1, //Until attention is aligned, testing only wastes computation time. "data_path": "/media/erogol/data_ssd/Data/LJSpeech-1.1", // DATASET-RELATED: can overwritten from command argument - "meta_file_train": "metadata.txt", // DATASET-RELATED: metafile for training dataloader. + "meta_file_train": "metadata_train.txt", // DATASET-RELATED: metafile for training dataloader. "meta_file_val": "metadata_val.txt", // DATASET-RELATED: metafile for evaluation dataloader. "dataset": "mozilla", // 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": 150, // DATASET-RELATED: maximum text length - "output_path": "../keep/", // DATASET-RELATED: output path for all training outputs. + "output_path": "/media/erogol/data_ssd/Data/models/mozilla_models/", // DATASET-RELATED: output path for all training outputs. "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.