app.py

# from speechbrain.inference.ASR import EncoderASR
# import gradio as gr

# model = EncoderASR.from_hparams("speechbrain/asr-wav2vec2-dvoice-wolof")

# def transcribe(audio):
#   return model.transcribe_file(audio.name)


# demo = gr.Interface(fn=transcribe, inputs="file", outputs="text", 
#                    title="Transcription automatique du wolof", 
#              description="Ce modèle transcrit un fichier audio en wolof en texte en utilisant l'alphabet latin.",              
#              input_label="Audio en wolof", 
#              output_label="Transcription alphabet latin"
#                    )

# demo.launch()


from speechbrain.inference.ASR import EncoderASR
import gradio as gr

model = EncoderASR.from_hparams("speechbrain/asr-wav2vec2-dvoice-wolof")

def transcribe(audio):
    sr, y = audio
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))

    return transcriber({"sampling_rate": sr, "raw": y})["text"]


demo = gr.Interface(
    transcribe,
    gr.Audio(sources=["microphone"]),
    "text",
)

demo.launch()