Hugging Face's logo

kotoba-tech
/
kotoba-whisper-v2.1

Automatic Speech Recognition
Transformers
Safetensors
Japanese
whisper
audio
hf-asr-leaderboard
Inference Endpoints
Model card Files Community
1
kotoba-whisper-v2.1
File size: 4,998 Bytes 
fb72b03
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
 
from pprint import pprint
from datasets import load_dataset
from transformers.pipelines import pipeline

model_alias = "kotoba-tech/kotoba-whisper-v1.1"

print("""### P + S ###""")
pipe = pipeline(model=model_alias,
                punctuator=True,
                stable_ts=True,
                chunk_length_s=15,
                batch_size=16,
                trust_remote_code=True)
dataset = load_dataset("kotoba-tech/kotoba-whisper-eval", split="train")
for i in dataset:
    if i["audio"]["path"] == "long_interview_1.mp3":
        i["audio"]["array"] = i["audio"]["array"][:7938000]
    prediction = pipe(
        i["audio"],
        return_timestamps=True,
        generate_kwargs={"language": "japanese", "task": "transcribe"}
    )
    pprint(prediction)
    break

print("""### P ###""")
pipe = pipeline(model=model_alias,
                punctuator=True,
                stable_ts=False,
                chunk_length_s=15,
                batch_size=16,
                trust_remote_code=True)
dataset = load_dataset("kotoba-tech/kotoba-whisper-eval", split="train")
for i in dataset:
    if i["audio"]["path"] == "long_interview_1.mp3":
        i["audio"]["array"] = i["audio"]["array"][:7938000]
    prediction = pipe(
        i["audio"],
        return_timestamps=True,
        generate_kwargs={"language": "japanese", "task": "transcribe"}
    )
    pprint(prediction)
    break

print("""### S ###""")
pipe = pipeline(model=model_alias,
                punctuator=False,
                stable_ts=True,
                chunk_length_s=15,
                batch_size=16,
                trust_remote_code=True)
dataset = load_dataset("kotoba-tech/kotoba-whisper-eval", split="train")
for i in dataset:
    if i["audio"]["path"] == "long_interview_1.mp3":
        i["audio"]["array"] = i["audio"]["array"][:7938000]
    prediction = pipe(
        i["audio"],
        return_timestamps=True,
        generate_kwargs={"language": "japanese", "task": "transcribe"}
    )
    pprint(prediction)
    break

print("""### RAW ###""")
pipe = pipeline(model=model_alias,
                punctuator=False,
                stable_ts=False,
                chunk_length_s=15,
                batch_size=16,
                trust_remote_code=True)
dataset = load_dataset("kotoba-tech/kotoba-whisper-eval", split="train")
for i in dataset:
    if i["audio"]["path"] == "long_interview_1.mp3":
        i["audio"]["array"] = i["audio"]["array"][:7938000]
    prediction = pipe(
        i["audio"],
        return_timestamps=True,
        generate_kwargs={"language": "japanese", "task": "transcribe"}
    )
    pprint(prediction)
    break

print("""### P + S ###""")
pipe = pipeline(model=model_alias,
                punctuator=True,
                stable_ts=True,
                chunk_length_s=15,
                batch_size=16,
                trust_remote_code=True)
dataset = load_dataset("kotoba-tech/kotoba-whisper-eval", split="train")
for i in dataset:
    if i["audio"]["path"] == "long_interview_1.mp3":
        i["audio"]["array"] = i["audio"]["array"][:7938000]
    prediction = pipe(
        i["audio"],
        generate_kwargs={"language": "japanese", "task": "transcribe"}
    )
    pprint(prediction)
    break

print("""### P ###""")
pipe = pipeline(model=model_alias,
                punctuator=True,
                stable_ts=False,
                chunk_length_s=15,
                batch_size=16,
                trust_remote_code=True)
dataset = load_dataset("kotoba-tech/kotoba-whisper-eval", split="train")
for i in dataset:
    if i["audio"]["path"] == "long_interview_1.mp3":
        i["audio"]["array"] = i["audio"]["array"][:7938000]
    prediction = pipe(
        i["audio"],
        generate_kwargs={"language": "japanese", "task": "transcribe"}
    )
    pprint(prediction)
    break

print("""### S ###""")
pipe = pipeline(model=model_alias,
                punctuator=False,
                stable_ts=True,
                chunk_length_s=15,
                batch_size=16,
                trust_remote_code=True)
dataset = load_dataset("kotoba-tech/kotoba-whisper-eval", split="train")
for i in dataset:
    if i["audio"]["path"] == "long_interview_1.mp3":
        i["audio"]["array"] = i["audio"]["array"][:7938000]
    prediction = pipe(
        i["audio"],
        generate_kwargs={"language": "japanese", "task": "transcribe"}
    )
    pprint(prediction)
    break

print("""### RAW ###""")
pipe = pipeline(model=model_alias,
                punctuator=False,
                stable_ts=False,
                chunk_length_s=15,
                batch_size=16,
                trust_remote_code=True)
dataset = load_dataset("kotoba-tech/kotoba-whisper-eval", split="train")
for i in dataset:
    if i["audio"]["path"] == "long_interview_1.mp3":
        i["audio"]["array"] = i["audio"]["array"][:7938000]
    prediction = pipe(
        i["audio"],
        generate_kwargs={"language": "japanese", "task": "transcribe"}
    )
    pprint(prediction)
    break