Hugging Face's logo

Spaces:
langtech-veu
/
asr-inference-cs
Running

App Files Community
1
asr-inference-cs
File size: 1,458 Bytes 
90d343a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
import gradio as gr
from  whisper_cs import generate
from AinaTheme import theme  
import spaces

USE_V2 = False

@spaces.GPU
def transcribe(inputs, model_version):
    if inputs is None:
        raise gr.Error("Cap fitxer d'脿udio introduit! Si us plau pengeu un fitxer "\
                       "o enregistreu un 脿udio abans d'enviar la vostra sol路licitud")

    use_v2 = model_version == "v2.0"
    return generate(audio_path=inputs, use_v2=use_v2)

description_string = "Transcripci贸 autom脿tica de micr貌fon o de fitxers d'脿udio.\n Aquest demostrador s'ha desenvolupat per"\
              " comprovar els models de reconeixement de parla per a m贸bils."

def clear():
    return None, "v1.0"

with gr.Blocks() as demo:
    gr.Markdown(description_string)
    with gr.Row():
        with gr.Column(scale=1):
            model_version = gr.Dropdown(label="Model Version", choices=["v1.0", "v2.0"], value="v1.0")
            input = gr.Audio(sources=["upload", "microphone"], type="filepath", label="Audio")

        with gr.Column(scale=1):
            output = gr.Textbox(label="Output", lines=8)

    with gr.Row(variant="panel"):
        clear_btn = gr.Button("Clear")
        submit_btn = gr.Button("Submit", variant="primary")

    submit_btn.click(fn=transcribe, inputs=[input, model_version], outputs=[output])
    clear_btn.click(fn=clear, inputs=[], outputs=[input, model_version], queue=False)

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