From 5b5b9fcfdde67899031ac3eab7d2f5b52de6dd40 Mon Sep 17 00:00:00 2001 From: erogol Date: Mon, 26 Oct 2020 16:46:50 +0100 Subject: [PATCH] wavegrad config updates --- TTS/vocoder/configs/wavegrad_libritts.json | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/TTS/vocoder/configs/wavegrad_libritts.json b/TTS/vocoder/configs/wavegrad_libritts.json index 9bb1154b..64958da2 100644 --- a/TTS/vocoder/configs/wavegrad_libritts.json +++ b/TTS/vocoder/configs/wavegrad_libritts.json @@ -30,11 +30,11 @@ "symmetric_norm": true, // move normalization to range [-1, 1] "max_norm": 4.0, // scale normalization to range [-max_norm, max_norm] or [0, max_norm] "clip_norm": true, // clip normalized values into the range. - "stats_path": "/home/erogol/Data/libritts/LibriTTS/scale_stats.npy" // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored + "stats_path": "/home/erogol/Data/libritts/LibriTTS/scale_stats_wavegrad.npy" // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored }, // DISTRIBUTED TRAINING - "apex_amp_level": null, // APEX amp optimization level. "O1" is currently supported. + "apex_amp_level": "O1", // APEX amp optimization level. "O1" is currently supported. "distributed":{ "backend": "nccl", "url": "tcp:\/\/localhost:54322" @@ -45,8 +45,8 @@ // MODEL PARAMETERS "generator_model": "wavegrad", "model_params":{ - "x_conv_channels":32, - "c_conv_channels":768, + "y_conv_channels":32, + "x_conv_channels":768, "ublock_out_channels": [512, 512, 256, 128, 128], "dblock_out_channels": [128, 128, 256, 512], "upsample_factors": [4, 4, 4, 2, 2], @@ -62,15 +62,15 @@ "data_path": "/home/erogol/Data/libritts/LibriTTS/train-clean-360/", // root data path. It finds all wav files recursively from there. "feature_path": null, // if you use precomputed features "seq_len": 6144, // 24 * hop_length - "pad_short": 2000, // additional padding for short wavs + "pad_short": 0, // additional padding for short wavs "conv_pad": 0, // additional padding against convolutions applied to spectrograms "use_noise_augment": false, // add noise to the audio signal for augmentation - "use_cache": true, // use in memory cache to keep the computed features. This might cause OOM. + "use_cache": false, // use in memory cache to keep the computed features. This might cause OOM. "reinit_layers": [], // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers. // TRAINING - "batch_size": 64, // Batch size for training. + "batch_size": 96, // Batch size for training. "train_noise_schedule":{ "min_val": 1e-6, "max_val": 1e-2, @@ -87,7 +87,7 @@ // OPTIMIZER "epochs": 10000, // total number of epochs to train. - "clip_grad": 1, // Generator gradient clipping threshold. Apply gradient clipping if > 0 + "clip_grad": 1.0, // Generator gradient clipping threshold. Apply gradient clipping if > 0 "lr_scheduler": "MultiStepLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate "lr_scheduler_params": { "gamma": 0.5, @@ -96,16 +96,16 @@ "lr": 1e-4, // Initial learning rate. If Noam decay is active, maximum learning rate. // TENSORBOARD and LOGGING - "print_step": 25, // Number of steps to log traning on console. + "print_step": 50, // Number of steps to log traning on console. "print_eval": false, // If True, it prints loss values for each step in eval run. "save_step": 10000, // Number of training steps expected to plot training stats on TB and save model checkpoints. "checkpoint": true, // If true, it saves checkpoints per "save_step" - "tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. + "tb_model_param_stats": true, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. // DATA LOADING "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. - "eval_split_size": 10, + "eval_split_size": 256, // PATHS "output_path": "/home/erogol/Models/LJSpeech/"