coqui-tts/TTS/tts/models
Khalid Bashir 42afad5e79
Fixed bug related to yourtts speaker embeddings issue (#2234)
* Fixed bug related to yourtts speaker embeddings issue

* Reverted code for base_tts

* Bug fix on VITS d_vector_file type

* Ignore the test speakers on YourTTS recipe

* Add speaker encoder model and config on YourTTS recipe to easily do zero-shot inference

* Update YourTTS config file

* Update ModelManager._update_path to deal with list attributes

* Fix lint checks

* Remove unused code

* Fix unit tests

* Reset name_to_id to get the right speaker ids on load_embeddings_from_list_of_files

* Set weighted_sampler_multipliers as an empty dict to prevent users' mistakes

Co-authored-by: Edresson Casanova <edresson1@gmail.com>
2023-01-02 14:20:02 +01:00
..
__init__.py Update setup_model 2022-02-25 11:11:35 +01:00
align_tts.py Cache fsspec downloads (#2132) 2022-11-09 22:12:48 +01:00
base_tacotron.py Cache fsspec downloads (#2132) 2022-11-09 22:12:48 +01:00
base_tts.py Fixup overflow (#2218) 2022-12-15 00:56:48 +01:00
forward_tts.py Cache fsspec downloads (#2132) 2022-11-09 22:12:48 +01:00
glow_tts.py Fix for FloorDiv Function Warning (#1760) 2022-07-20 11:31:22 +02:00
overflow.py Fixup overflow (#2218) 2022-12-15 00:56:48 +01:00
tacotron.py Capacitron (#977) 2022-05-20 16:17:11 +02:00
tacotron2.py Capacitron (#977) 2022-05-20 16:17:11 +02:00
vits.py Fixed bug related to yourtts speaker embeddings issue (#2234) 2023-01-02 14:20:02 +01:00