File size: 1,801 Bytes
50af8e7
62c62a8
 
 
 
50af8e7
 
62c62a8
 
 
 
 
 
 
 
b3ad65b
62c62a8
50af8e7
 
 
62c62a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from faster_whisper import WhisperModel
import gradio as gr



model_path = "./model"
model = WhisperModel(model_path)#, device="cpu"




def process_file(in_filename: str,):
    if in_filename is None or in_filename == "":
        return "Error: No file"

    segments, info = model.transcribe(in_filename, language="uk", beam_size=5, without_timestamps=True, temperature = 0.01)

    transcript = ""
    for segment in segments:
        transcript += segment.text

    return transcript




demo = gr.Blocks()

with demo:
    with gr.Tabs():
        with gr.TabItem("Upload from disk"):
            uploaded_file = gr.Audio(
                source="upload",  # Choose between "microphone", "upload"
                type="filepath",
                optional=False,
                label="Upload from disk",
            )
            upload_button = gr.Button("Submit for recognition")
            uploaded_output = gr.Textbox(label="Recognized speech from uploaded file")

        with gr.TabItem("Record from microphone"):
            microphone = gr.Audio(
                source="microphone",  # Choose between "microphone", "upload"
                type="filepath",
                optional=False,
                label="Record from microphone",
            )

            record_button = gr.Button("Submit for recognition")
            recorded_output = gr.Textbox(label="Recognized speech from recordings")

        upload_button.click(
            process_file,
            inputs=[
                uploaded_file,
            ],
            outputs=[uploaded_output],
        )

        record_button.click(
            process_file,
            inputs=[
                microphone,
            ],
            outputs=[recorded_output],
        )


if __name__ == "__main__":
    demo.launch()