TELEVAL/requirements_all.txt at master · Tele-AI/TELEVAL · GitHub

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
79
80
81
# ======= basic ===========
jinja2
tqdm
requests
pandas
regex
datasets
soundfile
librosa

# average
torch==2.6.0
torchaudio==2.6.0
transformers==4.45.0
huggingface_hub==0.25.2
flash-attn==2.7.2.post1
accelerate>=0.26.0

# minicpm
pillow
vector-quantize-pytorch==1.18.5
vocos==0.1.0

# speech-gpt2
einops

# baichuan
av==12.3.0
fire==0.4.0
ujson==5.10.0
easydict==1.13
diffusers==0.27.2
deepspeed
decord==0.6.0
opencv-python==4.10.0.84
imagesize==1.4.1
cairosvg==2.7.1

# glm4voice
hyperpyyaml
tiktoken
conformer==0.3.2
lightning==2.2.4
rich==13.7.1
gdown==5.1.0
wget==3.2
matplotlib

# lamma-omni
openai-whisper==20240930
fairseq==0.12.2

# qwen2.5-omni
qwen-omni-utils==0.0.4
# transformers==4.52.3

# kimi
loguru
blobfile
timm
torchdyn==1.0.6
# transformers>=4.48.3

# stepaudio2-mini
#transformers==4.49.0
s3tokenizer

# mimoaudio
#transformers==4.49.0


# ============ evaluate ==============
WeTextProcessing
json-repair
#vllm  # choice
jiwer==4.0.0
funasr
zhon
zhconv
onnxruntime==1.18.1
scipy