app.py

import gradio as gr
import nemo.collections.asr as nemo_asr

asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/stt_en_conformer_ctc_large")

def transcription(audio):
  return asr_model.transcribe([audio.name])[0]
  
examples = [
    ['TestAudio1.wav']
]

css = """
footer {display:none !important}
.output-markdown{display:none !important}
.gr-button-primary {
    z-index: 14;
    height: 43px;
    width: 130px;
    left: 0px;
    top: 0px;
    padding: 0px;
    cursor: pointer !important; 
    background: none rgb(17, 20, 45) !important;
    border: none !important;
    text-align: center !important;
    font-family: Poppins !important;
    font-size: 14px !important;
    font-weight: 500 !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;
}
.gr-button-primary:hover{
    z-index: 14;
    height: 43px;
    width: 130px;
    left: 0px;
    top: 0px;
    padding: 0px;
    cursor: pointer !important;
    background: none rgb(37, 56, 133) !important;
    border: none !important;
    text-align: center !important;
    font-family: Poppins !important;
    font-size: 14px !important;
    font-weight: 500 !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;
}
"""

demo = gr.Interface(fn = transcription, inputs = gr.inputs.Audio(label="Input Audio", type="file"), outputs = gr.outputs.Textbox(label="Transcription"), examples = examples, css = css)
demo.launch()