Hugging Face's logo

Spaces:
laubonghaudoi
/
cantonese-srt
Sleeping

App Files Community
1
cantonese-srt
File size: 2,475 Bytes 
1d7163f
 
7ee40ec
1d7163f
 
 
 
 
 
 
 
 
 
 
 
 
 
7ee40ec
1d7163f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d10d964
 
 
1d7163f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163d736
 
 
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
 
import logging
import tempfile
import spaces

import gradio as gr

from transcriber import AutoTranscriber
from utils import to_srt

# Configure logging
logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
    force=True,
)
logger = logging.getLogger(__name__)

@spaces.GPU
def transcribe_audio(audio_path):
    """Process audio file and return SRT content and preview text"""
    try:
        transcriber = AutoTranscriber(
            corrector="opencc",
            use_denoiser=False,
            with_punct=False
        )

        transcribe_results = transcriber.transcribe(audio_path)

        if not transcribe_results:
            return None, "無字幕生成， 可能係檢測唔到語音。"

        # Generate SRT text for both preview and download
        srt_text = to_srt(transcribe_results)

        # Create temporary file for download
        with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.srt', encoding='utf-8') as tmp:
            tmp.write(srt_text)
            return tmp.name, srt_text

    except Exception as e:
        logger.error(f"Error during transcription: {str(e)}")
        return None, f"Error: {str(e)}"


def create_ui():
    with gr.Blocks() as demo:
        gr.Markdown("# 粵文字幕生成器")
        gr.Markdown(
            "上傳一個音頻文件，撳「生成字幕」，過一陣就會得到 SRT 文件，撳右下方藍色個「XY.Z KB ⇣」下載個 SRT。")
        gr.Markdown("目前支援格式：.mp3、.wav、.flac、.m4a、.webm。其他格式可能都可以，但唔保證成功。")
        gr.Markdown("注意：越長嘅音頻轉寫時間越長，請耐心等待。太長嘅音頻（半個鐘以上）有可能會爆 Error，重試幾次就可以。")

        with gr.Row():
            audio_input = gr.Audio(type="filepath", label="上傳音頻文件或者錄音")

        with gr.Row():
            generate_btn = gr.Button("生成字幕 SRT 文件", variant="primary", scale=2)

        with gr.Row():
            with gr.Column():
                preview = gr.Textbox(label="預覽生成字幕", lines=10)

            with gr.Column():
                output = gr.File(label="下載 SRT")

        generate_btn.click(
            fn=transcribe_audio,
            inputs=[audio_input],
            outputs=[output, preview]
        )

    return demo


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