TTS/requirements.txt

# core deps
numpy==1.22.0;python_version<="3.10"
numpy>=1.24.3;python_version>"3.10"
cython>=0.29.30
scipy>=1.11.2
torch>=2.1
torchaudio
soundfile>=0.12.0
librosa>=0.10.0
scikit-learn>=1.3.0
numba==0.55.1;python_version<"3.9"
numba>=0.57.0;python_version>="3.9"
inflect>=5.6.0
tqdm>=4.64.1
anyascii>=0.3.0
pyyaml>=6.0
fsspec>=2023.6.0 # <= 2023.9.1 makes aux tests fail
aiohttp>=3.8.1
packaging>=23.1
# deps for examples
flask>=2.0.1
# deps for inference
pysbd>=0.3.4
# deps for notebooks
umap-learn>=0.5.1
pandas>=1.4,<2.0
# deps for training
matplotlib>=3.7.0
# coqui stack
trainer>=0.0.32
# config management
coqpit>=0.0.16
# chinese g2p deps
jieba
pypinyin
# korean
hangul_romanize
# gruut+supported langs
gruut[de,es,fr]==2.2.3
# deps for korean
jamo
nltk
g2pkk>=0.1.1
# deps for bangla
bangla
bnnumerizer
bnunicodenormalizer
#deps for tortoise
einops>=0.6.0
transformers>=4.33.0
#deps for bark
encodec>=0.1.1
# deps for XTTS
unidecode>=1.3.2
num2words
spacy[ja]>=3
Update requirements.txt 2022-02-03 14:48:16 +00:00			`# core deps`
Fixups 2023-06-26 10:55:18 +00:00			`numpy==1.22.0;python_version<="3.10"`
Update versions 2023-11-17 11:10:46 +00:00			`numpy>=1.24.3;python_version>"3.10"`
			`cython>=0.29.30`
Updated scipy version (#2914) 2023-09-04 09:39:19 +00:00			`scipy>=1.11.2`
PyTorch 2.1 Updates (Weight Norm and TorchAudio I/O) (#3176) * Replaced PyTorch weight_norm With parametrizations.weight_norm * TorchAudio: Migrating The I/O Functions To Use The Dispatcher Mechanism * Corrected Code Style --------- Co-authored-by: Eren Gölge <erogol@hotmail.com> 2023-11-09 15:31:03 +00:00			`torch>=2.1`
Update requirements.txt 2022-02-03 14:48:16 +00:00			`torchaudio`
Update versions 2023-11-17 11:10:46 +00:00			`soundfile>=0.12.0`
			`librosa>=0.10.0`
			`scikit-learn>=1.3.0`
Update numba version (#2435) 2023-03-21 10:40:42 +00:00			`numba==0.55.1;python_version<"3.9"`
Update versions 2023-11-17 11:10:46 +00:00			`numba>=0.57.0;python_version>="3.9"`
			`inflect>=5.6.0`
			`tqdm>=4.64.1`
			`anyascii>=0.3.0`
			`pyyaml>=6.0`
			`fsspec>=2023.6.0 # <= 2023.9.1 makes aux tests fail`
			`aiohttp>=3.8.1`
			`packaging>=23.1`
Update requirements.txt 2022-02-03 14:48:16 +00:00			`# deps for examples`
Update versions 2023-11-17 11:10:46 +00:00			`flask>=2.0.1`
Update requirements.txt 2022-02-03 14:48:16 +00:00			`# deps for inference`
Update versions 2023-11-17 11:10:46 +00:00			`pysbd>=0.3.4`
Update requirements.txt 2022-02-03 14:48:16 +00:00			`# deps for notebooks`
Update versions 2023-11-17 11:10:46 +00:00			`umap-learn>=0.5.1`
requirements.txt: loosen pandas pin (1.4 would need to be compiled from source on macs) 2023-09-26 17:43:59 +00:00			`pandas>=1.4,<2.0`
Update requirements.txt 2022-02-03 14:48:16 +00:00			`# deps for training`
Update versions 2023-11-17 11:10:46 +00:00			`matplotlib>=3.7.0`
Update requirements.txt 2022-02-03 14:48:16 +00:00			`# coqui stack`
Ensures that only GPT model is in training mode during XTTS GPT training (#3241) * Ensures that only GPT model is in training mode during training * Fix parallel wavegan unit test 2023-11-17 14:13:46 +00:00			`trainer>=0.0.32`
Update Coqpit requirement (#1539) 2022-04-26 15:39:36 +00:00			`# config management`
			`coqpit>=0.0.16`
Update requirements.txt 2022-02-03 14:48:16 +00:00			`# chinese g2p deps`
			`jieba`
			`pypinyin`
XTTS v2.0 (#3137) * Implement most similar ref training approach * Use non-enhanced hifigan for test samples * Add Perceiver * Update GPT Trainer for perceiver support * Update XTTS docs * Bug fix masking with XTTS perceiver * Bug fix on gpt forward * Bug Fix on XTTS v2.0 training * Add XTTS v2.0 unit tests * Add XTTS v2.0 inference unit tests * Bug Fix on diffusion inference * Add XTTS v2.0 training recipe * Placeholder model entry * Add cloning params to config * Make prompt embedding configurable * Make cloning configurable * Cheap fix for a cheaper fix * Prevent resampling * Update model entry * Update docs * Update requirements * Code linting * Add xtts v2 to sep tests * Bug fix on XTTS get_gpt_cond_latents * Bug fix on rebase * Make style * Bug fix in Japenese tokenizer * Add num2words to deps * Remove unused kwarg and added num_beams=1 as default --------- Co-authored-by: Eren G??lge <egolge@coqui.ai> 2023-11-06 13:58:18 +00:00			`# korean`
			`hangul_romanize`
Use gruut for phonemization 2021-06-02 14:35:59 +00:00			`# gruut+supported langs`
Add FR and ES gruut languages as requirement to avoid inference issues (#2572) * Add all gruut supported languages as requeriment to avoid inference issues * Remove unused gruut languages 2023-05-03 12:49:01 +00:00			`gruut[de,es,fr]==2.2.3`
Korean Phonemizer (#1822) * Update requirements.txt install jamo for korean * Update formatters.py add KSS formatter KSS is a korean single speech dataset (12hours) * Add files via upload add phonemizer for korean * Add files via upload add korean phonemizer * Update requirements.txt * change code style with `black` and `pylint` * reflecting pylint's Evaluation * reflecting pylint's Evaluation * reflecting pylint's Evaluation-2 * isort * edit about separator write test case and add 'nltk' for requirements.txt * add korean g2p (g2pkk) * isort * TTS/tts/utils/text/phonemizers/ko_kr_phonemizer.py:43:24: W0621: Redefining name 'text' from outer scope (line 58) (redefined-outer-name) TTS/tts/utils/text/korean/korean.py:28:8: R1705: Unnecessary "else" after "return" (no-else-return) * black 2022-09-08 10:06:07 +00:00			`# deps for korean`
Lower the versions constraints 2023-09-25 15:00:41 +00:00			`jamo`
			`nltk`
numpy version for py310 (#2316) * numpy version for py310 requested in #2315 * Update requirements.txt 2023-02-13 09:34:00 +00:00			`g2pkk>=0.1.1`
Add BN requirements 2023-04-17 10:54:14 +00:00			`# deps for bangla`
Lower the versions constraints 2023-09-25 15:00:41 +00:00			`bangla`
			`bnnumerizer`
			`bnunicodenormalizer`
Tortoise TTS inference (#2547) * initial commit * Tortoise inference * revert path change * style fix * remove accidental remove * style fixes * style fixes * removed unwanted assests and deps * remove changes * remove cvvp * style fix black * added tortoise config and updated config and args, refactoring the code * added tortoise to api * Pull mel_norm from url * Use TTS cleaners * Let download model files * add ability to pass tortoise presets through coqui api * fix tests * fix style and tests * fix tts commandline for tortoise * Add config.json to tortoise * Use kwargs * Use regular model api for loading tortoise * Add load from dir to synthesizer * Fix Tortoise floats * Use model_dir when there are multiple urls * Use `synthesize` when exists * lint fixes and resolve preset bug * resolve a download bug and update model link * fix json * do tortoise inference from voice dir * fix * fix test * fix speaker id and remove assests * update inference_tests.yml * replace inference_test.yml * fix extra dir as None * fix tests * remove space * Reformat docstring * Add docs * Update docs * lint fixes --------- Co-authored-by: Eren Gölge <egolge@coqui.ai> Co-authored-by: Eren Gölge <erogol@hotmail.com> 2023-05-15 22:58:21 +00:00			`#deps for tortoise`
Update versions 2023-11-17 11:10:46 +00:00			`einops>=0.6.0`
			`transformers>=4.33.0`
Inference API for 🐶Bark (#2685) * Add bark requirements * Draft Bark implementation * Download HF models * Update synthesizer * Add bark model * Make style * Update pylintrc * Update model URLs * Update Bark Config * Fix here and ther * Make style * Make lint * Update requirements * Update requirements 2023-06-28 09:55:27 +00:00			`#deps for bark`
Update versions 2023-11-17 11:10:46 +00:00			`encodec>=0.1.1`
Fixup 2023-09-13 16:21:44 +00:00			`# deps for XTTS`
Update versions 2023-11-17 11:10:46 +00:00			`unidecode>=1.3.2`
XTTS v2.0 (#3137) * Implement most similar ref training approach * Use non-enhanced hifigan for test samples * Add Perceiver * Update GPT Trainer for perceiver support * Update XTTS docs * Bug fix masking with XTTS perceiver * Bug fix on gpt forward * Bug Fix on XTTS v2.0 training * Add XTTS v2.0 unit tests * Add XTTS v2.0 inference unit tests * Bug Fix on diffusion inference * Add XTTS v2.0 training recipe * Placeholder model entry * Add cloning params to config * Make prompt embedding configurable * Make cloning configurable * Cheap fix for a cheaper fix * Prevent resampling * Update model entry * Update docs * Update requirements * Code linting * Add xtts v2 to sep tests * Bug fix on XTTS get_gpt_cond_latents * Bug fix on rebase * Make style * Bug fix in Japenese tokenizer * Add num2words to deps * Remove unused kwarg and added num_beams=1 as default --------- Co-authored-by: Eren G??lge <egolge@coqui.ai> 2023-11-06 13:58:18 +00:00			`num2words`
Add sentence splitting (#3227) * Add sentence spliting * update requirements * update default args v2 * Add spanish * Fix return gpt_latents * Update requirements * Fix requirements 2023-11-16 10:01:11 +00:00			`spacy[ja]>=3`