import torch # import gradio as gr from transformers import pipeline import numpy as np from flask import Flask, jsonify, request from werkzeug.utils import secure_filename from flask_cors import CORS import os ALLOWED_EXTENSIONS = set(['xls', 'csv', 'png', 'jpeg', 'jpg','wav']) UPLOAD_FOLDER = os.path.abspath(os.path.join(os.path.dirname(__file__), 'Downloads')) app = Flask(__name__) app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER app.config['MAX_CONTENT_LENGTH'] = 500 * 1000 * 1000 # 500 MB app.config['CORS_HEADER'] = 'application/json' device = 0 if torch.cuda.is_available() else "cpu" transcriber = pipeline("automatic-speech-recognition", model="jonatasgrosman/wav2vec2-large-xlsr-53-english",device=device) def allowedFile(filename): return '.' in filename and \ filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS @app.route('/') def home(): return 'Hello, World!' @app.route('/upload', methods=['POST', 'GET']) def fileUpload(): if request.method == 'POST': file = request.files.getlist('files') filename = "" print(request.files, "....") for f in file: textz = transcribe(f.read()) print(textz) print(f.filename) filename = secure_filename(f.filename) print(allowedFile(filename)) if allowedFile(filename): f.save(os.path.join(app.config['UPLOAD_FOLDER'], filename)) else: return jsonify({'message': 'File type not allowed'}), 400 return jsonify({"name": filename, "status": "success"}) else: return jsonify({"status": "Upload API GET Request Running"}) @app.route('/speech-to-text', methods=['POST']) def speech_to_text(): print(flask.request.data) return flask.request.files # Convert audio data to numpy array y = np.frombuffer(audio_data, dtype=np.float32) # Reshape the array if needed (depends on the format of the audio data) # y = np.reshape(y, (-1,)) # Call the transcribe function text = transcribe(y) # Return the transcription return flask.jsonify({'text': text}) def transcribe(new_chunk): y = np.frombuffer(new_chunk, dtype=np.float32) sr = 16000 return transcriber({"sampling_rate": sr, "raw": y})["text"]