wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-11 12:00:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

REBASED: Transform Speaker Encoder in a Generic Encoder and Implement Emotion Encoder training support (#1349)

Browse Source 
* Rename Speaker encoder module to encoder

* Add a generic emotion dataset formatter

* Transform the Speaker Encoder dataset to a generic dataset and create emotion encoder config

* Add class map in emotion config

* Add Base encoder config

* Add evaluation encoder script

* Fix the bug in plot_embeddings

* Enable Weight decay for encoder training

* Add argumnet to disable storage

* Add Perfect Sampler and remove storage

* Add evaluation during encoder training

* Fix lint checks

* Remove useless config parameter

* Active evaluation in speaker encoder test and use multispeaker dataset for this test

* Unit tests fixs

* Remove useless tests for speedup the aux_tests

* Use get_optimizer in Encoder

* Add BaseEncoder Class

* Fix the unitests

* Add Perfect Batch Sampler unit test

* Add compute encoder accuracy in a function
This commit is contained in:
Edresson Casanova
2022-03-11 14:43:40 +01:00
committed by GitHub
parent 36e9ea2f97
commit f81892483d
40 changed files with 962 additions and 2791 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/inputs/test_speaker_encoder_config.json
+2 -2
View File
@@ -36,8 +36,8 @@
"warmup_steps": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
"steps_plot_stats": 10, // number of steps to plot embeddings.
"num_speakers_in_batch": 64, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
"num_utters_per_speaker": 10, //
"num_classes_in_batch": 64, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
"num_utter_per_class": 10, //
"num_loader_workers": 8, // number of training data loader processes. Don't set it too big. 4-8 are good values.
"wd": 0.000001, // Weight decay weight.
"checkpoint": true, // If true, it saves checkpoints per "save_step"