File size: 3,467 Bytes
13b9ce8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2a44a58
 
 
591b040
2a44a58
 
 
 
 
 
 
 
 
 
 
 
591b040
2a44a58
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13b9ce8
 
 
 
 
 
 
 
 
 
 
 
 
 
2a44a58
 
13b9ce8
 
 
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
import torch

import gradio as gr
import pytube as pt
from transformers import pipeline
from huggingface_hub import model_info

MODEL_NAME = "openai/whisper-small" #this always needs to stay in line 8 :D sorry for the hackiness
lang = "en"

device = 0 if torch.cuda.is_available() else "cpu"
pipe = pipeline(
    task="automatic-speech-recognition",
    model=MODEL_NAME,
    chunk_length_s=30,
    device=device,
)

pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")

def transcribe(microphone, file_upload):
    warn_output = ""
    if (microphone is not None) and (file_upload is not None):
        warn_output = (
            "WARNING: You've uploaded an audio file and used the microphone. "
            "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
        )

    elif (microphone is None) and (file_upload is None):
        return "ERROR: You have to either use the microphone or upload an audio file"

    file = microphone if microphone is not None else file_upload

    text = pipe(file)["text"]

    return warn_output + text

demo = gr.Blocks()

css = """
footer {display:none !important}
.output-markdown{display:none !important}
button.primary {
    z-index: 14;
    left: 0px;
    top: 0px;
    cursor: pointer !important; 
    background: none rgb(17, 20, 45) !important;
    border: none !important;
    color: rgb(255, 255, 255) !important;
    line-height: 1 !important;
    border-radius: 12px !important;
    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
    box-shadow: none !important;
}
button.primary:hover{
    z-index: 14;
    left: 0px;
    top: 0px;
    cursor: pointer !important;
    background: none rgb(37, 56, 133) !important;
    border: none !important;
    color: rgb(255, 255, 255) !important;
    line-height: 1 !important;
    border-radius: 12px !important;
    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
    box-shadow: rgb(0 0 0 / 23%) 0px 1px 7px 0px !important;
}
.hover\:bg-orange-50:hover {
    --tw-bg-opacity: 1 !important;
    background-color: rgb(229,225,255) !important;
}
.to-orange-200 {
    --tw-gradient-to: rgb(37 56 133 / 37%) !important;
}
.from-orange-400 {
    --tw-gradient-from: rgb(17, 20, 45) !important;
    --tw-gradient-to: rgb(255 150 51 / 0);
    --tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to) !important;
}
.group-hover\:from-orange-500{
    --tw-gradient-from:rgb(17, 20, 45) !important; 
    --tw-gradient-to: rgb(37 56 133 / 37%);
    --tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to) !important;
}
.group:hover .group-hover\:text-orange-500{
    --tw-text-opacity: 1 !important;
    color:rgb(37 56 133 / var(--tw-text-opacity)) !important;
}
"""

examples = [
    ['TestAudio1.mp3'], ['TestAudio2.wav'], ['TestAudio3.wav'], ['TestAudio4.wav'], ['TestAudio5.wav'], ['TestAudio6.wav'], ['TestAudio7.wav'], ['TestAudio8.wav'], ['TestAudio9.wav'], ['TestAudio10.wav']
]

mf_transcribe = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
        gr.inputs.Audio(source="upload", type="filepath", optional=True)
    ],
    outputs="text",
    layout="horizontal",
    theme="huggingface",
    allow_flagging="never",
    examples = examples,
    css = css
).launch(enable_queue=True)

#used openai/whisper model