coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
4,454 Commits
80 Branches
98 Tags
316 MiB
Commit Graph

4454 Commits (revert-3038-xtts_redonwload)

Author SHA1 Message Date
Eren Gölge e33e7170ed Bump up to v0.13.1 2023-04-12 16:20:53 +02:00
Eren Gölge 8da3342676 Ping API 2023-04-12 16:20:53 +02:00
Eren Gölge 73d963718a
Merge pull request #2495 from coqui-ai/api_voice_conversion 
Api voice conversion
 2023-04-11 16:40:14 +02:00
Eren Gölge cbb592b295 Fixup 2023-04-10 14:50:11 +02:00
Eren Gölge b8b9f09de5 Fixup 2023-04-10 14:06:31 +02:00
Eren Gölge 76511972e9 Add freevc to the models list 2023-04-10 14:03:08 +02:00
Eren Gölge 209f0a509a Add voice conversion api tes 2023-04-10 13:37:47 +02:00
Eren Gölge a49c1931d9 Fixup 2023-04-10 13:33:42 +02:00
Eren Gölge 5bd1fb6b2c Fix API for voice conversion 2023-04-10 13:32:16 +02:00
Eren Gölge 30109af2a0
Merge pull request #2480 from MattyB95/librosa_v0.10.0 
Update Librosa Version To V0.10.0
 2023-04-07 12:32:33 +02:00
Matthew Boakes 5bdd6f7c18 Updated Librosa Dependency Specification 2023-04-06 12:36:24 +01:00
Eren Gölge 1233365cf4 Bump up to v0.13.0 2023-04-05 15:09:31 +02:00
Eren Gölge ad8b9bf2be
🐸 Coqui Studio API integration (#2484) 
* Warn when lang is not avail

* Make style

* Implement Coqui Studio API

* Test

* Update docs

* Set action

* Make style

* Make lint

* Update README

* Make style

* Fix action

* Run actions
 2023-04-05 15:06:50 +02:00
Wesley Pyburn ce79160576
Fix errors in README.md (#2478) 
Running the sample code below results in an error `language_id = self.tts_model.language_manager.name_to_id[language_name]`.
The fix is running the code with the correct language strings, the readme has been updated in this PR to work.

I assume this small typo leads to #2456 and #2458
 2023-04-05 12:23:07 +02:00
Matthew Boakes 4c829e74a1 Update Librosa Version To V0.10.0 2023-04-05 00:59:20 +01:00
Yingzhi WANG 95fa2c9fd6
fix typo (#2475) 2023-04-03 23:31:09 +02:00
p0p 91cf1b2da9
[minor] batch["speaker_ids"] getting set two times (#2470) 
* [minor] batch["speaker_ids"] getting set two times

just to make it consistent with language_ids

* Update vits.py

style.
 2023-04-03 11:35:21 +02:00
Rajiv P c2d15cd413
[minor] hifigan_generator.py typo (#2462) 
resblock2 description updated.
 2023-03-28 12:43:36 +02:00
Eren Gölge d309f50e53
Implement FreeVC (#2451) 
* Update .gitignore

* Draft FreeVC implementation

* Tests and relevant updates

* Update API tests

* Add missings

* Update requirements

* :(

* Lazy handle for vc

* Update docs for voice conversion

* Make style
 2023-03-25 18:33:23 +01:00
Eren Gölge 090cadf270
Update numba version (#2435) 2023-03-21 11:40:42 +01:00
Khalid Bashir 14c80dd1fd
vits.py training fixed due to return_complex (#2418) 
Torch set default value for `return_complex=True` for `torch.stft` method
This turned warning into error:-
```
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1591, in fit
    self._fit()
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1544, in _fit
    self.train_epoch()
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1309, in train_epoch
    _, _ = self.train_step(batch, batch_num_steps, cur_step, loader_start_time)
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1162, in train_step
    outputs, loss_dict_new, step_time = self._optimize(
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1023, in _optimize
    outputs, loss_dict = self._model_train_step(batch, model, criterion, optimizer_idx=optimizer_idx)
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 970, in _model_train_step
    return model.train_step(*input_args)
  File "/workspace/coqui-tts/TTS/tts/models/vits.py", line 1293, in train_step
    mel_slice_hat = wav_to_mel(
  File "/workspace/coqui-tts/TTS/tts/models/vits.py", line 191, in wav_to_mel
    spec = torch.stft(
  File "/usr/local/lib/python3.10/dist-packages/torch/functional.py", line 641, in stft
    return _VF.stft(input, n_fft, hop_length, win_length, window,  # type: ignore[attr-defined]
RuntimeError: stft requires the return_complex parameter be given for real inputs, and will further require that return_complex=True in a future PyTorch release.
```
 2023-03-19 00:22:04 +01:00
Eren Gölge 12f3365185 Merge branch 'dev' 2023-03-17 13:31:08 +01:00
Eren Gölge 2db262747e
Bump up to v0.12.0 2023-03-17 13:21:03 +01:00
Roee Shenberg 3c15f0619a
Bug fixes in OverFlow audio generation (#2380) 2023-03-15 12:02:11 +01:00
Eren Gölge b8d9837d27
Merge pull request #2407 from dveni/patch-1 
Update vits.py
 2023-03-14 10:28:23 +01:00
Daniel Vera Nieto dfb48737fb Style fixed 2023-03-13 16:11:15 +01:00
Eren Gölge 9bb62c570d
Merge pull request #2390 from coqui-ai/dev 
v0.12.0
 2023-03-13 12:43:38 +01:00
Eren Gölge c10f9a3699
Update docs (#2389) 
* Update docs index

* Add MarryTTS docs

* Update docs index

* Add Overflow docs
 2023-03-13 12:42:20 +01:00
Eren Gölge 4ca07514d4
Remove doc bot (#2399) 2023-03-13 12:42:01 +01:00
Dani Vera 0d12229b64
Update vits.py 
This should fix the issue https://github.com/coqui-ai/TTS/issues/1986 without breaking batch data sampling.
 2023-03-10 18:35:16 +01:00
manmay nakhashi 624513018d
add energy by default to Fastspeech2 config (#2326) 
* add energy by default

* added energy to base tts

* fix energy dataset

* fix styles

* fix test
 2023-03-06 10:20:25 +01:00
Florian Quirin 478c8178b8
Basic Mary-TTS API compatibility (#2352) 
* added basic Mary-TTS API endpoints to server

- imported `parse_qs` from `urllib.parse` to parse HTTP POST parameters
- imported `render_template_string` from `flask` to return text as endpoint result
- added new routes:
  - `/locales` - returns list of locales (currently locale of active model)
  - `/voices` - returns list of voices (currently locale and name of active model)
  - `/process` - accepts synth. request (GET and POST) with parameter `INPUT_TEXT` (other parameters ignored since we have only one active model)

* better log messages for Mary-TTS API

- smaller tweaks to log output

* use f-string in log print to please linter

* updated server.py to match 'make style' result
 2023-03-06 10:08:21 +01:00
thennal10 d39bc74f57
OverFlow with test sentences (#2253) 
* Fix typo in function definiton

* Swap hasattr out

hasattr(self, "speaker_manager")  and hasattr(self, "language_manager") seems to be redundant since BaseTTS defines both.
 2023-03-01 09:11:30 +01:00
Edresson Casanova 16b9862252
Fix Speaker Consistency Loss (SCL) (#2364) 2023-02-27 09:14:00 +03:00
p0p4k a365a7e888
numpy version for py310 (#2316) 
* numpy version for py310

requested in #2315

* Update requirements.txt
 2023-02-13 10:34:00 +01:00
Eren G??lge d488b4f1c6 Merge branch 'dev' into main 2023-02-10 17:39:37 +01:00
Eren G??lge 661725b95e Bump up to v0.11.1 2023-02-10 15:59:05 +01:00
Eren G??lge 0196b4dfbf Merge branch 'add_neural_hmm_model' into dev 2023-02-10 15:23:56 +01:00
Eren G??lge ea5bd7dcbc Merge branch 'dev' into main 2023-02-10 10:27:34 +01:00
Eren Gölge 914280a556
Bump up to v0.11.0 (#2329) 
* Make style

* Bump up to v0.11.0
 2023-02-08 13:58:49 +01:00
Eren G??lge 6cfb590eb2 Merge branch 'dev' into main 2023-02-06 11:47:18 +01:00
Eren G??lge 683b4d432f Fixup 2023-02-06 11:44:56 +01:00
Eren G??lge c7184dcef9 Linter fix 2023-02-06 11:30:36 +01:00
Eren G??lge 910a218652 Merge branch 'dev' into main 2023-02-06 11:25:33 +01:00
Eren G??lge 4e75b6262c Update docs 2023-02-06 11:20:32 +01:00
Eren G??lge 85b3a04b37 Merge branch 'api_model_path' into dev 2023-02-06 11:18:00 +01:00
Eren G??lge c496b1a986 Linter fix 2023-02-06 11:17:28 +01:00
Eren G??lge baed2a2c2b Update README 2023-02-06 11:15:43 +01:00
marius851000 1f4d8bf0f1
Fix tts-server for multi-lingual models (#2257) 2023-02-06 10:54:34 +01:00
Eren G??lge 6ee94f8bad Fixup 2023-01-30 14:02:25 +01:00