coqui-tts/TTS
Enno Hermann 39321d02be
fix: correctly strip/restore initial punctuation (#3336)
* refactor(punctuation): remove orphan code for handling lone punctuation

The case of lone punctuation is already handled at the top of restore(). The
removed if statement would never be called and would in fact raise an
AttributeError because the _punc_index named tuple doesn't have the attribute
`mark`.

* refactor(punctuation): remove unused argument

* fix(punctuation): correctly handle initial punctuation

Stripping and restoring initial punctuation didn't work correctly because the
string-splitting caused an additional empty string to be inserted in the text
list (because `".A".split(".")` => `["", "A"]`). Now, an initial empty string is
skipped and relevant test cases are added.

Fixes #3333
2023-11-30 13:03:16 +01:00
..
bin fix(bin.synthesize): more informative error for wrong --language argument (#3294) 2023-11-24 12:24:42 +01:00
config Fix model tests (#2943) 2023-09-14 15:21:48 +02:00
encoder refactor: use save_checkpoint()/save_best_model() from Trainer 2023-11-17 01:18:23 +01:00
server Make style 2023-08-11 12:55:23 +02:00
tts fix: correctly strip/restore initial punctuation (#3336) 2023-11-30 13:03:16 +01:00
utils Make text splitting optional 2023-11-27 14:53:11 +01:00
vc PyTorch 2.1 Updates (Weight Norm and TorchAudio I/O) (#3176) 2023-11-09 16:31:03 +01:00
vocoder Ensures that only GPT model is in training mode during XTTS GPT training (#3241) 2023-11-17 15:15:22 +01:00
.models.json Update to XTTS v2.0.3 2023-11-24 14:36:04 +01:00
VERSION Update to v0.21.1 2023-11-24 15:15:44 +01:00
__init__.py Use `coqui_tts` as the default run name 2021-08-30 12:56:47 +00:00
api.py Fixup 2023-11-28 13:47:45 +01:00
cs_api.py Make style 2023-11-13 13:01:01 +01:00
model.py Cache fsspec downloads (#2132) 2022-11-09 22:12:48 +01:00