Dusty Hagstrom 13cd076a7f Synthesizer skips over embeddings file if model only has one speaker (#2587) ... * It looks like the Neon model is special in that t does not have a speaker_name and it wants to get the only item available. This was blocking a valid model with one speaker and a d_vector_file from being executed to get the embedding. * Update synthesizer.py oh my how embarrassing		2023-10-16 11:55:45 +02:00
..
bin	Late-import main TTS libraries in `tts` CLI	2023-09-26 15:38:56 +03:00
config	Fix model tests (#2943)	2023-09-14 15:21:48 +02:00
encoder	Drop fairseq for Hubert	2023-06-26 19:27:48 +02:00
server	Make style	2023-08-11 12:55:23 +02:00
tts	unit test fix	2023-10-13 10:56:47 -03:00
utils	Synthesizer skips over embeddings file if model only has one speaker (#2587)	2023-10-16 11:55:45 +02:00
vc	Remove duplicate convert_pad_shape	2023-09-27 01:10:48 +03:00
vocoder	[minor] hifigan_generator.py typo (#2462)	2023-03-28 12:43:36 +02:00
.models.json	Streaming inference for XTTS 🚀 (#3035)	2023-10-06 18:34:06 +02:00
VERSION	v0.17.8	2023-10-07 01:14:05 +03:00
__init__.py	Use `coqui_tts` as the default run name	2021-08-30 12:56:47 +00:00
api.py	None is not able to be read for "XTTS", fixes crash if its set to None. (#3009)	2023-10-02 12:53:36 +02:00
cs_api.py	Update Studio API for XTTS (#2861)	2023-08-13 12:04:12 +02:00
model.py	Cache fsspec downloads (#2132)	2022-11-09 22:12:48 +01:00