-
-
Notifications
You must be signed in to change notification settings - Fork 31
/
requirements.linux.txt
78 lines (70 loc) · 1.54 KB
/
requirements.linux.txt
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
# numpy v1.23.4 required for whisper
numpy==1.24.2
tqdm==4.66.4
rich==12.6.0
more-itertools==10.3.0
librosa==0.10.2.post1
transformers==4.44.0
tensorboardX==2.6.2.2
accelerate==0.33.0
bitsandbytes
ffmpeg-python==0.2.0
click>=8.1.3
PyAudio==0.2.14
# PyAudioWPatch==0.2.12.6
resampy==0.4.3
sounddevice==0.4.7
SpeechRecognition==3.10.4
pydub>=0.25.1
git+https://github.com/openai/whisper.git
triton
soundfile==0.12.1
python-osc>=1.8.0
websockets>=10.4
unidecode==1.3.8
pykakasi>=2.2.1
ctranslate2==4.3.1
sentencepiece==0.2.0
protobuf==3.20.3
progressbar2==4.3.2
fasttext-wheel
robust-downloader
# pywin32
easyocr==1.7.1
mss==7.0.1
scipy==1.10.1
num2words==0.5.13
onnxruntime==1.18.1
requests==2.31.0
# downgradea of scikit-image to v1.19.3 to prevent https://github.com/scikit-image/scikit-image/issues/6784
scikit-image==v0.22.0
deepfilternet==0.5.6
pyloudnorm
nltk
# NVIDIA Nemo (Canary) dependency
huggingface-hub==0.23.2
youtokentome
git+https://github.com/NVIDIA/[email protected]#egg=nemo_toolkit[asr]
# plugin dependencies
omegaconf==2.2.3
PyYAML>=6.0
# winsdk>=1.0.0b9
keyboard>=0.13.5
grpcio==1.59.3
annotated_types==0.6.0
# for ChatTTS plugin
frozendict==2.4.4
# speaker diarization
pyannote.audio==3.2.0
#RVC dependencies
fairseq @ https://github.com/Sharrnah/fairseq/archive/refs/heads/py3.11.zip
faiss-cpu==1.7.4
praat-parselmouth>=0.4.2
pyworld==0.3.4
torchcrepe==0.0.22
faster-whisper
noisereduce
# Whisper Medusa dependencies (https://github.com/aiola-lab/whisper-medusa, https://huggingface.co/aiola/whisper-medusa-v1)
boto3==1.34.82
peft==0.6.2
wandb==0.16.6