app.py

import librosa
import gradio as gr
import numpy as np
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
import soundfile as sf
import torch

# load model and tokenizer
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")

def speech2text(audio):
    sr, data = audio

    # resample to 16hz
    data_16hz = librosa.resample(data[:,0].astype(np.float32),sr,16000)

    # tokenize
    input_values = processor([data_16hz], return_tensors="pt", padding="longest").input_values  # Batch size 1

    # retrieve logits
    logits = model(input_values).logits

    # take argmax and decode
    predicted_ids = torch.argmax(logits, dim=-1)
    transcription = processor.batch_decode(predicted_ids)

    return transcription[0].lower()  # batch size 1

iface = gr.Interface(speech2text, "microphone", "text")

iface.launch()