speech.py

#Build a shareable app with Gradio
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
#from datasets import load_dataset


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

from transformers import pipeline
asr = pipeline(task="automatic-speech-recognition",
               model="distil-whisper/distil-small.en") 
               
         
import os
import gradio as gr

demo = gr.Blocks()

def transcribe_speech(filepath):
    if filepath is None:
        gr.Warning("No audio found, please retry.")
        return ""
    output = asr(filepath)
    return output["text"]
    
mic_transcribe = gr.Interface(
    fn=transcribe_speech,
    inputs=gr.Audio(sources="microphone",
                    type="filepath"),
    outputs=gr.Textbox(label="Transcription",
                       lines=3),
    allow_flagging="never")
    
file_transcribe = gr.Interface(
    fn=transcribe_speech,
    inputs=gr.Audio(sources="upload",
                    type="filepath"),
    outputs=gr.Textbox(label="Transcription",
                       lines=3),
    allow_flagging="never",
)

with demo:
    gr.TabbedInterface(
        [mic_transcribe,
         file_transcribe],
        ["Transcribe Microphone",
         "Transcribe Audio File"],
    )

#demo.launch(server_port=int(os.environ['PORT1']))
demo.launch(server_port=int(os.environ.get('PORT1',8080)))

'''                       
                       
import soundfile as sf
import io
audio, sampling_rate = sf.read('output.wav')
print(audio.shape)   
'''