app.py

# -*- coding: utf-8 -*-
"""whisper_microphone.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1nvViL6jAkzpXX3quqkz2I44m70S-YN8t

# Using gradio for making a nice UI.
Upload audio file version.

Installing requirements.
"""

#!pip install gradio
#!pip install git+https://github.com/huggingface/transformers

from transformers import pipeline
import gradio as gr
import os

"""## Building a Demo

Now that we've fine-tuned our model we can build a demo to show 
off its ASR capabilities! We'll make use of 🤗 Transformers 
`pipeline`, which will take care of the entire ASR pipeline, 
right from pre-processing the audio inputs to decoding the 
model predictions.

Running the example below will generate a Gradio demo where can input audio to 
our fine-tuned Whisper model to transcribe the corresponding text:
"""

from transformers import WhisperTokenizer
from transformers import WhisperProcessor



pipe = pipeline(model="Victorlopo21/whisper-medium-gl-30")
  # change to "your-username/the-name-you-picked"

def transcribe(audio):
    text = pipe(audio)['text']
    return text

iface = gr.Interface(
    fn=transcribe, 
    inputs=gr.Audio(source='microphone', type="filepath"),
    outputs="text",
    title="Whisper Medium Galician",
    description="Realtime demo for Galician speech recognition using a fine-tuned Whisper medium model.",
)

iface.launch(debug=True)

# TO TRY