Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
4,917 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

2112 Commits

Author SHA1 Message Date
Enno Hermann 6f25c2b904 refactor(delightful_tts): remove unused classes 2024-11-23 01:04:17 +01:00
Enno Hermann 7cdfde226b refactor: move amp_to_db/db_to_amp into torch_transforms 2024-11-23 01:04:17 +01:00
Enno Hermann 33ac0d6ee1 refactor(xtts): use build_hf_gpt_transformer from tortoise 2024-11-21 15:44:42 +01:00
Enno Hermann 490c973371 refactor(xtts): use position embedding from tortoise 2024-11-21 15:44:42 +01:00
Enno Hermann 5ffc0543b7 refactor(bark): remove custom layer norm 
Pytorch LayerNorm supports bias=False since version 2.1
 2024-11-21 15:44:42 +01:00
Enno Hermann 705551c60c refactor(tortoise): remove unused do_checkpoint arguments 
These are assigned but not used for anything.
 2024-11-21 15:44:42 +01:00
Enno Hermann 4ba83f42ab chore(tortoise): remove unused AudioMiniEncoder 
There's one in tortoise.classifier that's actually used
 2024-11-21 15:44:42 +01:00
Enno Hermann 66701e1e51 refactor(xtts): reuse functions/classes from tortoise 2024-11-21 12:51:42 +01:00
Enno Hermann 1f27f994a1 refactor(utils): remove duplicate set_partial_state_dict 2024-11-21 11:53:35 +01:00
Enno Hermann 1b6d3ebd33 refactor(xtts): remove duplicate hifigan generator 2024-11-21 11:53:35 +01:00
Enno Hermann fbbae5ac6a refactor(audio): remove duplicate rms_volume_norm function 2024-11-18 10:01:52 +01:00
Enno Hermann 8ba3233ec6 refactor(audio): remove duplicate save_wav code 2024-11-18 10:01:50 +01:00
Enno Hermann 5784f6705a refactor(audio): improve type hints, address lint issues 2024-11-18 10:00:55 +01:00
Enno Hermann 48f5be2ccb feat(audio): automatically convert audio to mono 2024-11-18 01:11:43 +01:00
Enno Hermann 627bbe4150 fix(xtts): more helpful error message when vocab.json not found 2024-11-17 00:30:32 +01:00
Enno Hermann e81f8d079c fix: more helpful error message when formatter is not found 2024-11-17 00:29:49 +01:00
Enno Hermann 993da778b4 chore: use original instead of scarf urls 
These allowed Coqui to get download stats, which we don't need anymore
 2024-11-10 22:19:25 +01:00
Enno Hermann 2df9bfa78e
refactor: handle deprecation of torch.cuda.amp.autocast (#144) 
torch.cuda.amp.autocast(args...) and torch.cpu.amp.autocast(args...) will be
deprecated. Please use torch.autocast("cuda", args...) or torch.autocast("cpu",
args...) instead.

https://pytorch.org/docs/stable/amp.html
 2024-11-09 18:37:08 +01:00
Shavit 540e8d6cf2
fix(bin.synthesize): return speakers names only (#147) 2024-11-09 18:35:54 +01:00
Enno Hermann 0971bc236e refactor: use external package for monotonic alignment 2024-11-08 12:35:04 +01:00
Enno Hermann 6314032fd7
Merge pull request #113 from idiap/pytorch 
fix: only enable load with weights_only in pytorch>=2.4
 2024-11-04 22:14:42 +01:00
Enno Hermann 8e66be2c32 fix: only enable load with weights_only in pytorch>=2.4 
Allows moving the minimum Pytorch version back to 2.1
 2024-11-04 18:39:51 +01:00
Enno Hermann 47ad0bf190
fix(text.characters): add nasal diacritic (#127) 2024-11-04 17:40:23 +01:00
Enno Hermann 964b813235 fix(gpt): set attention mask and address other warnings 2024-10-25 18:49:04 +02:00
Johnny Street 018d4ba1db fix(xtts): support transformers>=4.43.0 in streaming inference 2024-10-20 15:20:26 +02:00
Shavit 36611a7192
feat: normalize unicode characters in text cleaners (#85) 
* Add normalizer type C to text cleaners

* Linter recommendations

* Add unicode normalize to every cleaner

* Format test_text_cleaners.py
 2024-10-02 17:01:19 +02:00
Enno Hermann e5dd06b3bb
Merge pull request #77 from shavit/71-torch-load 
Load weights only in torch.load
 2024-09-12 23:28:57 +01:00
Enno Hermann 659b4852ba chore(bark): remove manual download of hubert model 
Bark was previously adapted to download Hubert from HuggingFace, so the manual
download is superfluous.
 2024-09-12 23:37:19 +02:00
Enno Hermann 86b58fb6d9 fix: define torch safe globals for torch.load 
Required for loading some models using torch.load(..., weights_only=True). This
is only available from Pytorch 2.4
 2024-09-12 23:37:19 +02:00
shavit 17ca24c3d6 fix: load weights only in torch.load 2024-09-12 23:37:19 +02:00
Enno Hermann 1920328822
feat(xtts): support hindi in tokenizer (#64) 
Added proper tokenizer support for Hindi Language which would prevent crash while fine tuning Hindi language.

Co-authored-by: Akshat Bhardwaj <157223825+akshatrocky@users.noreply.github.com>
 2024-09-12 21:29:21 +02:00
Enno Hermann 9c604c1de0 chore(dataset): address lint issues 2024-07-31 15:47:27 +02:00
Enno Hermann 8c460d0cd0 fix(dataset): skip files where audio length can't be computed 
Avoids hard failures when the audio can't be decoded.
 2024-07-31 15:20:56 +02:00
Daniel Walmsley 20bbb411c2
fix(xtts): update streaming for transformers>=4.42.0 (#59) 
* Fix Stream Generator on MacOS

* Make it work on mps

* Implement custom tensor.isin

* Fix for latest TF

* Comment out hack for now

* Remove unused code

* build: increase minimum transformers version

* style: fix

---------

Co-authored-by: Enno Hermann <Eginhard@users.noreply.github.com>
 2024-07-25 16:24:10 +02:00
Enno Hermann 20583a496e
Merge pull request #57 from idiap/xtts-vocab 
fix(xtts): load tokenizer file based on config as last resort
 2024-07-25 13:26:28 +01:00
Enno Hermann de35920317
Merge pull request #50 from idiap/umap 
build: move umap-learn into optional notebook dependencies
 2024-07-25 13:26:09 +01:00
Enno Hermann 9192ef1aa6 fix(xtts): load tokenizer file based on config as last resort 2024-07-05 13:52:01 +02:00
Abraham Mathews 6ea3b75b84
Update xtts.py (#53) 
docs(xtts): fix typo in example
 2024-07-02 13:43:52 +02:00
Enno Hermann 2d06aeb79b chore: remove unused TTS.utils.io module 
All uses of these methods were replaced with the equivalents from coqui-tts-trainer
 2024-06-29 15:07:10 +02:00
Enno Hermann e869b9b658 refactor: use load_checkpoint from trainer 2024-06-29 15:07:10 +02:00
Enno Hermann da82d55329 refactor: use load_fsspec from trainer 
Made automatically with:
rg "from TTS.utils.io import load_fsspec" --files-with-matches | xargs sed -i 's/from TTS.utils.io import load_fsspec/from trainer.io import load_fsspec/g'
 2024-06-29 15:07:10 +02:00
Enno Hermann 0fb26f97df refactor: use get_user_data_dir from trainer 2024-06-29 15:07:10 +02:00
Enno Hermann 28296c6458 refactor: use get_git_branch from trainer 2024-06-29 15:07:10 +02:00
Enno Hermann 59ef28d708 build: move umap-learn into optional notebook dependencies 
Except for notebooks, it's only used to show embedding plots during speaker
encoder training, in which case a warning is now shown to install it.
 2024-06-26 23:53:17 +02:00
Enno Hermann 4bd3df2607 refactor: remove duplicate get_padding 2024-06-26 11:54:36 +02:00
Enno Hermann c30fb0f56b chore: remove duplicate init_weights 2024-06-26 11:46:37 +02:00
Enno Hermann c5241d71ab chore: address pytorch deprecations 
torch.range(a, b) == torch.arange(a, b+1)

meshgrid indexing: https://github.com/pytorch/pytorch/issues/50276

checkpoint use_reentrant:
https://dev-discuss.pytorch.org/t/bc-breaking-update-to-torch-utils-checkpoint-not-passing-in-use-reentrant-flag-will-raise-an-error/1745

optimizer.step() before scheduler.step():
https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
 2024-06-26 11:38:25 +02:00
Enno Hermann a755328e49 refactor(freevc): remove duplicate sequence_mask 2024-06-26 10:17:04 +02:00
Enno Hermann f8df19a10c refactor: remove duplicate convert_pad_shape 2024-06-26 10:17:04 +02:00
Enno Hermann cd7b6daf46 fix: clarify types, fix missing functions 2024-06-26 10:17:04 +02:00