| import gradio as gr | |
| from speechbrain.pretrained import EncoderASR | |
| asr_model = EncoderASR.from_hparams(source="speechbrain/asr-wav2vec2-commonvoice-fr", savedir="pretrained_models/asr-wav2vec2-commonvoice-fr") | |
| def speech_recognize(file): | |
| text = asr_model.transcribe_file(file) | |
| return text | |
| iface = gr.Interface( | |
| fn=speech_recognize, | |
| inputs=gr.inputs.Audio(source="microphone", type='filepath'), | |
| outputs="text", | |
| ) | |
| iface.launch() | |