from speechbrain.inference.separation import SepformerSeparation as separator import torchaudio import gradio as gr model = separator.from_hparams(source="speechbrain/sepformer-wham16k-enhancement", savedir='pretrained_models/sepformer-wham16k-enhancement') def speechbrain(aud): # for custom file, change path est_sources = model.separate_file(path=aud) torchaudio.save("enhanced_wham16k.wav", est_sources[:, :, 0].detach().cpu(), 16000) return "enhanced_wham16k.wav" inputs = gr.inputs.Audio(label="Input Audio", type="filepath") outputs = [ gr.outputs.Audio(label="Output Audio", type="filepath"), ] title = "Speech Enhancer" description = "Gradio demo for Speech Enhance by SpeechBrain. To use it, simply upload your audio, or click one of the examples to load them" examples = [ ['example_wham16k.wav'] ] gr.Interface(speechbrain, inputs, outputs, title=title, description=description, article=article, examples=examples).launch()