import os os.system("pip install git+https://github.com/openai/whisper.git") import gradio as gr import whisper model = whisper.load_model("base") 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) print(f"Detected language: {max(probs, key=probs.get)}") options = whisper.DecodingOptions() result = whisper.decode(model, mel, options) print(result.text) return result.text title="Whisper" description="Whisper is a general-purpose speech recognition model. It is 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: 730px; 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( """

Whisper

Whisper is a general-purpose speech recognition model. It is 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.

""" ) with gr.Group(): with gr.Box(): 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) btn.click(inference, inputs=[audio], outputs=[text]) gr.HTML(''' ''') block.launch()