diff --git a/config.json b/config.json index 0c62e55b..f49eed79 100644 --- a/config.json +++ b/config.json @@ -1,6 +1,6 @@ { - "model_name": "embed_init_loss_weight", - "model_description": "Lower loss freq is weight 0.0, higher weight decay, ref_level_db: 40->20, sample_rate:16000 -> 22050", + "model_name": "queue", + "model_description": "Queue memory and change lower r incrementatlly", "audio":{ "audio_processor": "audio", // to use dictate different audio processors, if available. @@ -28,15 +28,16 @@ "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. - "lr": 0.001, // Initial learning rate. If Noam decay is active, maximum learning rate. + "lr": 0.0001, // Initial learning rate. If Noam decay is active, maximum learning rate. "lr_decay": false, // if true, Noam learning rate decaying is applied through training. "loss_weight": 0.0, // loss weight to emphasize lower frequencies. Lower frequencies are in general more important for speech signals. "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, // memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5. "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. + "r": 2, // Number of frames to predict for step. "wd": 0.00001, // 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. diff --git a/test_cluster.py b/test_cluster.py new file mode 100644 index 00000000..7f3cf221 --- /dev/null +++ b/test_cluster.py @@ -0,0 +1 @@ +print("Python is running!!") \ No newline at end of file