Eren Gölge 5911eec3b1 Small trainer refactoring ... 1. Use a single Gradscaler for all the optimizers 2. Save terminal logs to a file. In DDP mode, each worker creates `trainer_N_log.txt`. 3. Fixes to allow only the main worker (rank==0) writing to Tensorboard 4. Pass parameters owned by the target optimizer to the grad_clip_norm		2021-08-26 17:08:58 +00:00
..
__init__.py	fixing dome pypi issues	2021-01-25 13:06:12 +01:00
compute_attention_masks.py	Add 🐍 python 3.9 to CI	2021-06-28 17:03:47 +02:00
compute_embeddings.py	Add fullband-melgan DE vocoder	2021-07-26 15:38:30 +02:00
compute_statistics.py	Update `TTS.bin` scripts for the new API	2021-06-28 17:03:47 +02:00
convert_melgan_tflite.py	reformatting and styling	2021-04-12 11:47:39 +02:00
convert_melgan_torch_to_tf.py	Allow saving / loading checkpoints from cloud paths (#683)	2021-08-09 18:02:36 +00:00
convert_tacotron2_tflite.py	reformatting and styling	2021-04-12 11:47:39 +02:00
convert_tacotron2_torch_to_tf.py	Allow saving / loading checkpoints from cloud paths (#683)	2021-08-09 18:02:36 +00:00
distribute.py	Small trainer refactoring	2021-08-26 17:08:58 +00:00
extract_tts_spectrograms.py	Allow saving / loading checkpoints from cloud paths (#683)	2021-08-09 18:02:36 +00:00
find_unique_chars.py	Add fullband-melgan DE vocoder	2021-07-26 15:38:30 +02:00
resample.py	bumpup librosa version to 0.8.0	2021-05-03 14:25:09 +02:00
synthesize.py	Fix `num_char` init in Tacotron models	2021-08-09 21:46:15 +00:00
train_encoder.py	Update Logger API, recipes	2021-08-09 18:34:00 +00:00
train_tts.py	Unified logger API	2021-08-09 18:34:00 +00:00
train_vocoder.py	Unified logger API	2021-08-09 18:34:00 +00:00
tune_wavegrad.py	reformatting and styling	2021-04-12 11:47:39 +02:00