File size: 6,088 Bytes
f40e092
 
1c6d288
f40e092
1c6d288
f40e092
d089c2e
 
 
 
 
 
 
1c6d288
 
f40e092
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79b926e
f40e092
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9993123
f40e092
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9993123
f40e092
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6d8d501
 
f40e092
b3ed5a5
71086b1
f40e092
 
b3ed5a5
 
 
 
 
 
 
 
 
 
 
f40e092
 
79b926e
9dc7dd3
9993123
f40e092
 
 
 
 
 
d089c2e
a1036d7
d089c2e
 
f40e092
 
 
 
 
 
 
 
 
d089c2e
 
 
86f5d25
f40e092
d089c2e
 
f40e092
 
79b926e
f40e092
 
 
 
 
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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
import os
os.system("pip install git+https://github.com/openai/whisper.git")
import gradio as gr
import whisper

model = whisper.load_model("small")
current_size = 'small'

def change_model(size):
  if size == current_size:
    return
  model = whisper.load_model(size)
  current_size = size


def inference(audio):
    audio = whisper.load_audio(audio)
    audio = whisper.pad_or_trim(audio)
    
    mel = whisper.log_mel_spectrogram(audio).to(model.device)
    
    _, probs = model.detect_language(mel)
    
    options = whisper.DecodingOptions(fp16 = False)
    result = whisper.decode(model, mel, options)
    
    print(result.text)
    return result.text


title="Whisper OpenAI, deployed with jthteo"

description="Whisper is a general-purpose speech recognition model into English. It has been trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification."

css = """
        .gradio-container {
            font-family: 'IBM Plex Sans', sans-serif;
        }
        .gr-button {
            color: white;
            border-color: black;
            background: black;
        }
        input[type='range'] {
            accent-color: black;
        }
        .dark input[type='range'] {
            accent-color: #dfdfdf;
        }
        .container {
            max-width: 800px;
            margin: auto;
            padding-top: 1.5rem;
        }
     
        .details:hover {
            text-decoration: underline;
        }
        .gr-button {
            white-space: nowrap;
        }
        .gr-button:focus {
            border-color: rgb(147 197 253 / var(--tw-border-opacity));
            outline: none;
            box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
            --tw-border-opacity: 1;
            --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
            --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
            --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
            --tw-ring-opacity: .5;
        }
        .footer {
            margin-bottom: 45px;
            margin-top: 35px;
            text-align: center;
            border-bottom: 1px solid #e5e5e5;
        }
        .footer>p {
            font-size: .8rem;
            display: inline-block;
            padding: 0 10px;
            transform: translateY(10px);
            background: white;
        }
        .dark .footer {
            border-color: #303030;
        }
        .dark .footer>p {
            background: #0b0f19;
        }
        .prompt h4{
            margin: 1.25em 0 .25em 0;
            font-weight: bold;
            font-size: 115%;
        }
"""

block = gr.Blocks(css=css)

with block:
    gr.HTML(
        """
            <div style="text-align: center; max-width: 800px; margin: 0 auto;">
              <div
                style="
                  display: inline-flex;
                  align-items: center;
                  gap: 0.8rem;
                  font-size: 1.75rem;
                "
              >
                <svg
                  width="0.65em"
                  height="0.65em"
                  viewBox="0 0 115 115"
                  fill="none"
                  xmlns="http://www.w3.org/2000/svg"
                >
                  <circle cx="62" cy="45" r="36" stroke="blue" stroke-width="4" fill="blue" />
                  <polygon points="40, 30, 84, 30, 62, 69" style="fill:red;stroke:red;stroke-width:5;" />
                </svg>
                
                <h1 style="font-weight: 900; margin-bottom: 7px; color:red;">
                  Whisper
                </h1>
                
                <svg
                  width="0.65em"
                  height="0.65em"
                  viewBox="0 0 115 115"
                  fill="none"
                  xmlns="http://www.w3.org/2000/svg"
                >
                  <circle cx="62" cy="45" r="36" stroke="blue" stroke-width="4" fill="blue" />
                  <polygon points="40, 30, 84, 30, 62, 69" style="fill:red;stroke:red;stroke-width:5;" />
                </svg>
              </div>
              <p style="margin-bottom: 10px; font-size: 94%">
                Whisper is a general-purpose speech recognition model. It has been trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification. </p>
                <p>This is a fork by JTHTEO.</p>
                <p>The sizes of the different Whisper models can be found in this <a href="https://github.com/openai/whisper/blob/main/model-card.md">Model Card</a>. </p>
              </p>
            </div>
        """
    )
    with gr.Group():
        with gr.Box():
            wmodel = gr.Radio(
                        choices=["tiny", "base", "small", "medium", "large", "small.en", "medium.en"],
                        label="Model used",
                        value="small")
            with gr.Row().style(mobile_collapse=False, equal_height=True):
                audio = gr.Audio(
                    label="Input Audio",
                    show_label=False,
                    source="microphone",
                    type="filepath"
                )
                btn = gr.Button("Transcribe")
        text = gr.Textbox(show_label=False)

##events###
        wmodel.change(change_model, inputs=[wmodel], outputs=[])
        btn.click(inference, inputs=[audio], outputs=[text],api_name="audio_whisper")
 
 ##footer###
 
        gr.HTML('''
        <div class="footer">
                    <p>Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a> - Gradio Demo by 🤗 Hugging Face, this is a fork by JTHTEO
                    </p>
        </div>
        ''')

block.launch()