numpy
onnxruntime
quebra-frases
langcodes
ovos-number-parser>=0.4.0
ovos-date-parser>=0.6.4a1
scriptconv[phonemizers]>=0.0.4a25
unicode_rbnf
click
requests
huggingface_hub
json_database
ovos-plugin-manager>=2.1.0
ovos-utils
regex

[all]
scriptconv[ar-phonemizers,en-phonemizers,goruut,he,ja-phonemizers,phonemizers,pt,pt-phonemizers,stress,tashkeel,zh-phonemizers]>=0.0.4a23
stressonnx>=0.0.3a2
text2tashkeel
epitran
gruut[de]<3.0,>=2.3.0
gruut[en]<3.0,>=2.3.0
gruut[es]<3.0,>=2.3.0
gruut[fr]<3.0,>=2.3.0
gruut[it]<3.0,>=2.3.0
gruut[ja]<3.0,>=2.3.0
gruut[nl]<3.0,>=2.3.0
gruut[ru]<3.0,>=2.3.0
gruut[sv]<3.0,>=2.3.0
gruut[sw]<3.0,>=2.3.0
gruut[vi]<3.0,>=2.3.0
gruut[zh]<3.0,>=2.3.0
misaki[en]
misaki[ja]
misaki[vi]
misaki[zh]
ahotts-g2p>=0.1.0
spacy<4.0,>=3.7
pycotovia>=0.4.0a1
pykakasi==2.3.0
spacy-pkuseg
soundfile
scipy
orthography2ipa
arbtok
euskaphone
g2p_barranquenho
mwl_phonemizer
pydub
tokenizers
sentencepiece
safetensors
librosa<1,>=0.9.2
onnx<1.18
audiosronnx
voiceclonnx>=0.0.3a3

[ar]
epitran
arbtok
text2tashkeel

[audiosr]
audiosronnx

[ca]
epitran

[chatterbox-multilingual]
pykakasi==2.3.0
spacy-pkuseg

[cjk]
pykakasi==2.3.0
spacy-pkuseg

[cloning]
soundfile
scipy

[cs]
epitran

[de]
epitran
gruut[de]<3.0,>=2.3.0

[en]
epitran
gruut[en]<3.0,>=2.3.0
misaki[en]
spacy<4.0,>=3.7

[es]
epitran

[espeak]
espyak>=0.0.3a1

[eu]
ahotts-g2p>=0.1.0
euskaphone

[fa]
epitran

[fr]
epitran

[gl]
pycotovia>=0.4.0a1

[he]
epitran

[indic-parler]
tokenizers

[it]
epitran

[ja]
epitran
gruut[ja]<3.0,>=2.3.0
misaki[ja]
spacy<4.0,>=3.7

[ko]
epitran

[matcha]
scipy

[mwl]
mwl_phonemizer

[o2i]
orthography2ipa

[omnivoice]
pydub

[pockettts]
safetensors

[pt]
epitran
g2p_barranquenho

[ru]
epitran

[streaming]
onnx

[sv]
epitran

[sw]
epitran

[test]
pytest
torch<3,>=2.1
torchaudio
pytorch-lightning<3,>=2.0
ovos-plugin-manager>=2.1.0
pycotovia>=0.4.0a1
sentencepiece
ahotts-g2p>=0.1.0
espyak>=0.0.3a1
voiceclonnx>=0.0.3a3
orthography2ipa
arbtok
euskaphone
g2p_barranquenho
mwl_phonemizer
pypinyin>=0.50
gruut[en]<3.0,>=2.3.0
tokenizers
kittentts==0.1.3

[test:python_version < "3.13"]
misaki[en]
misaki[zh]
spacy<4.0,>=3.7
onnx<1.18

[test:python_version >= "3.13"]
onnx>=1.18
ml_dtypes>=0.5

[train]
diffusers<0.36,>=0.25.0
einops
huggingface_hub
librosa<1,>=0.9.2
pytorch-lightning<3,>=2.0
torch<3,>=2.1
tqdm
scipy

[train-data]
pandas
pyarrow
datasets
soundfile

[train-eval]
speechonnxmetrics
speechmos
torchaudio
soundfile
speakeronnx
vadonnx
onnx-asr
pandas

[train-fastpitch]

[train-mixer]

[train-mosstts]
sentencepiece
safetensors
soundfile
onnx

[train-optispeech]
pyloudnorm
scipy
torchaudio
onnx
opt_einsum

[train-pyworld]
pyworld>=0.3.2
setuptools<81

[train-resample]
torchaudio

[train-styletts2]
einops-exts
munch
transformers>=4.48
torchaudio
soundfile
pandas
PyYAML

[train:python_version < "3.13"]
numpy<2,>=1.19.0

[train:python_version >= "3.13"]
numpy>=2.1
numba>=0.66

[vc]
voiceclonnx>=0.0.3a3

[vi]
epitran
gruut[vi]<3.0,>=2.3.0
misaki[vi]
spacy<4.0,>=3.7

[zh]
epitran
gruut[zh]<3.0,>=2.3.0
misaki[zh]
spacy<4.0,>=3.7
