Commit Graph

  • cde319874e fix: support multi-speaker models in tts_with_vc/tts_with_vc_to_file Enno Hermann 2023-11-20 15:56:02 +0100
  • 8a7cc18494 Revert "fix for issue 3067" Enno Hermann 2023-11-20 15:18:12 +0100
  • 54592213f4
    load multilingual model by path TITC 2023-11-20 18:57:05 +0800
  • bfa0291a21 Introduced Dockerfile.dev, updated CONTRIBUTING Kaszanas 2023-11-18 17:34:36 +0100
  • 808fa49952 Moved Dockerfile back to main directory Kaszanas 2023-11-18 17:33:42 +0100
  • 59bba20069 Moved Dockerfile, COPY at the end Kaszanas 2023-11-18 15:35:12 +0100
  • dbfb719fe9 feature/ add back original doc shahbazraza 2023-11-18 13:58:51 +0500
  • 29dede20d3
    Merge pull request #3249 from coqui-ai/run_ci_for_v0.20.6 v0.20.6 Eren Gölge 2023-11-17 15:45:26 +0100
  • c011ab7455 Update to v0.20.6 run_ci_for_v0.20.6 Eren Gölge 2023-11-16 17:52:13 +0100
  • 52cb1e2f68 Update model hash for v2.0.2 Eren G??lge 2023-11-17 15:16:08 +0100
  • 6075fa208c Ensures that only GPT model is in training mode during XTTS GPT training (#3241) Edresson Casanova 2023-11-17 11:13:46 -0300
  • a3279f9294 Make style Eren G??lge 2023-11-17 13:43:34 +0100
  • f21067a84a Make k_diffusion optional Eren G??lge 2023-11-17 13:42:33 +0100
  • 44494daa27 Update CI version Eren G??lge 2023-11-17 13:01:32 +0100
  • c864acf2b7 Update versions Eren G??lge 2023-11-17 12:10:46 +0100
  • 11283fce07
    Ensures that only GPT model is in training mode during XTTS GPT training (#3241) Edresson Casanova 2023-11-17 11:13:46 -0300
  • 14579a4607
    Merge pull request #3248 from coqui-ai/slacker_deps Eren Gölge 2023-11-17 15:13:19 +0100
  • 44880f09ed Make style Eren G??lge 2023-11-17 13:43:34 +0100
  • 26efdf6ee7 Make k_diffusion optional Eren G??lge 2023-11-17 13:42:33 +0100
  • 08d11e9198 Update CI version Eren G??lge 2023-11-17 13:01:32 +0100
  • 63d7145647 Update versions Eren G??lge 2023-11-17 12:10:46 +0100
  • 92264dac94 Add short timeout to check_config WeberJulian 2023-11-17 11:57:57 +0100
  • 0fb0d67de7 refactor: use save_checkpoint()/save_best_model() from Trainer Enno Hermann 2023-11-17 00:39:11 +0100
  • 96678c7ba2 refactor: use copy_model_files() from Trainer Enno Hermann 2023-11-17 00:12:09 +0100
  • 5119e651a1 chore(utils.io): remove unused code Enno Hermann 2023-11-16 23:52:28 +0100
  • 39fe38bda4 refactor: use save_fsspec() from Trainer Enno Hermann 2023-11-16 23:46:26 +0100
  • fdf0c8b10a chore(encoder): remove unused code Enno Hermann 2023-11-16 23:40:21 +0100
  • 5f0d7c52a8 fix Chinese lang from 'zh' to 'zh-cn' Bojie Li 2023-11-16 21:51:16 +0000
  • c18ec9f9ca Fix parallel wavegan unit test Edresson Casanova 2023-11-16 17:19:31 -0300
  • b87a665a40 Ensures that only GPT model is in training mode during training Edresson Casanova 2023-11-16 14:41:12 -0300
  • 7e4375da2b
    Update to v0.20.6 Eren Gölge 2023-11-16 17:52:13 +0100
  • fbc18b8c34
    Fix zh bug (#3238) Julian Weber 2023-11-16 17:51:37 +0100
  • 2150199f78 Fix zh bug WeberJulian 2023-11-16 17:25:02 +0100
  • 675f983550
    Add sentence splitting (#3227) Julian Weber 2023-11-16 11:01:11 +0100
  • 3c2d5a9e03
    Remove duplicate AudioProcessor code and fix ExtractTTSpectrogram.ipynb (#3230) Enno Hermann 2023-11-16 10:57:06 +0100
  • 8f1db7510a refactor(audio.processor): remove duplicate quantization methods Enno Hermann 2023-11-15 16:19:56 +0100
  • ddbaecdb5b fix(ExtractTTSpectrogram.ipynb): adapt to current TTS code Enno Hermann 2023-11-15 15:52:57 +0100
  • aa0fbdf27e fix(bin.extract_tts_spectrograms): set quantization bits Enno Hermann 2023-11-14 14:07:36 +0100
  • 13e640f17e refactor(audio.processor): use load_wav from numpy_transforms Enno Hermann 2023-11-14 13:46:57 +0100
  • 9a43eafd60 refactor(audio.processor): use volume_norm from numpy_transforms Enno Hermann 2023-11-14 13:40:56 +0100
  • 0a0e7a3bae refactor(audio.processor): use trim_silence from numpy_transforms Enno Hermann 2023-11-14 13:39:37 +0100
  • 842a632cd5 refactor(audio.processor): use find_endpoint from numpy_transforms Enno Hermann 2023-11-14 13:37:43 +0100
  • 5232bf9e36 chore(audio.processor): remove duplicate assert Enno Hermann 2023-11-14 13:33:51 +0100
  • b620092865 refactor(audio.processor): use rms_volume_norm from numpy_transforms Enno Hermann 2023-11-14 13:28:36 +0100
  • 11e98d3dac refactor(audio.processor): use pre-/deemphasis from numpy_transforms Enno Hermann 2023-11-14 13:25:35 +0100
  • f37cc4c028 refactor(audio.processor): remove duplicate stft_parameters Enno Hermann 2023-11-14 10:58:33 +0100
  • da229f3912 refactor(audio.processor): remove duplicate build_mel_basis Enno Hermann 2023-11-14 10:49:26 +0100
  • 754877784b refactor(audio.processor): remove duplicate mel_to_linear Enno Hermann 2023-11-14 10:44:35 +0100
  • fd9d6d4b0f refactor(audio.processor): remove duplicate linear_to_mel Enno Hermann 2023-11-14 10:41:01 +0100
  • 4fd5c46937 refactor(audio.processor): remove duplicate amp_to_db Enno Hermann 2023-11-13 21:54:02 +0100
  • 794f41c611 refactor(audio.processor): remove duplicate db_to_amp Enno Hermann 2023-11-13 21:49:45 +0100
  • 5a5da76260 chore(audio.processor): remove unused compute_stft_paddings Enno Hermann 2023-11-13 21:48:55 +0100
  • d75879802a refactor(audio.processor): remove duplicate stft+griffin_lim Enno Hermann 2023-11-13 21:47:36 +0100
  • 6471273c1d
    Merge pull request #3226 from coqui-ai/dev Eren Gölge 2023-11-15 15:34:29 +0100
  • 491f16ec37 Fix requirements WeberJulian 2023-11-15 15:23:55 +0100
  • 1bb689aa9f Update requirements WeberJulian 2023-11-15 15:22:10 +0100
  • 83988c922a Fix return gpt_latents WeberJulian 2023-11-15 14:37:53 +0100
  • d64cafccd2 Add spanish WeberJulian 2023-11-15 14:35:30 +0100
  • 2d9525a669 update default args v2 WeberJulian 2023-11-15 14:30:48 +0100
  • b5abb06dd9 update requirements WeberJulian 2023-11-15 14:28:03 +0100
  • 0abda77b39 Add sentence spliting WeberJulian 2023-11-15 14:26:57 +0100
  • 88630c60e5
    Update to v0.20.5 v0.20.5 Eren Gölge 2023-11-15 14:02:51 +0100
  • 73a5bd08c0
    Fix XTTS GPT padding and inference issues (#3216) Edresson Casanova 2023-11-15 10:02:05 -0300
  • 15f0ac57d6
    Update README.md (#3215) Ikko Eltociear Ashimine 2023-11-15 21:59:56 +0900
  • f5fd31f8e8 Remove ununsed code Edresson Casanova 2023-11-14 13:39:37 -0300
  • b231ca8878 Bug fix on zh-cn inference Edresson Casanova 2023-11-14 13:30:12 -0300
  • 7bfd20e692 Fix end artifact for fine tuning models Edresson Casanova 2023-11-11 12:37:44 -0300
  • 58082d197c
    Update README.md Ikko Eltociear Ashimine 2023-11-15 00:50:29 +0900
  • 04901fb2e4
    Add speed control for inference (#3214) Julian Weber 2023-11-14 16:07:17 +0100
  • 5a31ac788f Add speed control tests WeberJulian 2023-11-14 14:36:27 +0100
  • f20fa19efa Fix XTTS tests WeberJulian 2023-11-14 14:26:54 +0100
  • 9c8ead23e8
    Merge pull request #3210 from coqui-ai/dev Eren Gölge 2023-11-14 12:21:45 +0100
  • b3b22a04ca Add speed control for inference WeberJulian 2023-11-14 11:53:52 +0100
  • ac273d8361 feature/remove textfile args from synthesize.py from doc shahbazraza 2023-11-14 11:06:23 +0500
  • 45cc9ac757 feature/remove textfile args from readme.md shahbazraza 2023-11-14 10:38:04 +0500
  • 8fa4de1c8c chore: remove unused argument Enno Hermann 2023-11-13 21:43:06 +0100
  • d96f3885d5
    Update to v0.20.4 v0.20.4 Eren Gölge 2023-11-13 17:07:25 +0100
  • ac3df409a6
    Merge pull request #3208 from coqui-ai/fix_max_mel_len Eren Gölge 2023-11-13 14:32:56 +0100
  • f32a465711
    Merge pull request #3207 from coqui-ai/update_xtts_cloning Eren Gölge 2023-11-13 14:32:43 +0100
  • 92fa988aec Fixup update_xtts_cloning Eren G??lge 2023-11-13 13:44:06 +0100
  • b85536b23f fix max generation length WeberJulian 2023-11-13 13:18:45 +0100
  • b2682d39c5 Make style Eren G??lge 2023-11-13 13:01:01 +0100
  • a16360af85 Implement chunking gpt_cond Eren G??lge 2023-11-13 13:00:08 +0100
  • 5bc99fc81a
    Fixed markdown on installation.md Pol Vallverdu 2023-11-12 16:24:39 +0100
  • 39aeeedaec
    don't print if quiet=True Chris 2023-11-12 12:26:57 +0000
  • d0c8645183 feature/remove docs in inference shahbazraza 2023-11-11 22:45:21 +0500
  • 63b0e1a6ca feature/add args textfile in the docs shahbazraza 2023-11-11 10:48:46 +0500
  • 1b7f9348ce feature/add file upload option in UI shahbazraza 2023-11-11 10:47:58 +0500
  • 9498b0a51e feature/ test args textfile shahbazraza 2023-11-11 10:46:43 +0500
  • 5476023278 feature/ added args textfile shahbazraza 2023-11-11 10:45:27 +0500
  • f4773224cb
    Merge pull request #3183 from coqui-ai/dev Eren Gölge 2023-11-10 12:00:11 +0100
  • 6f1cba2f81
    Update to v0.20.3 v0.20.3 Eren Gölge 2023-11-09 17:41:37 +0100
  • 3b1e7038bc
    fix(formatters): set missing root_path attribute (#3182) Enno Hermann 2023-11-09 16:49:52 +0100
  • a8e9163fb3
    xtts/tokenizer: merge duplicate implementations of preprocess_text (#3170) Aarni Koskela 2023-11-09 17:32:12 +0200
  • 1b9c400bca
    PyTorch 2.1 Updates (Weight Norm and TorchAudio I/O) (#3176) Matthew Boakes 2023-11-09 15:31:03 +0000
  • 96174f2148
    Merge branch 'dev' into PyTorch2.1 Eren Gölge 2023-11-09 16:30:10 +0100
  • 66a1e248d0
    torchaudio should use proper backend to load audio (#3179) Gorkem 2023-11-09 18:28:39 +0300
  • 522a5a9c46 fix(formatters): set missing root_path attribute Enno Hermann 2023-11-09 14:46:21 +0100
  • 491f5eea0e torchaudio should use proper backend to load audio gorkemgoknar 2023-11-09 15:48:04 +0300
  • 2deccb6eb3 Corrected Code Style Matthew Boakes 2023-11-08 20:05:55 +0000