Update app.py

app.py

@@ -1,66 +1,22 @@
-import base64
-import json
-from flask import Flask, render_template, request
-from worker import speech_to_text, text_to_speech, openai_process_message
-from flask_cors import CORS
-import os
-
-app = Flask(__name__)
-cors = CORS(app, resources={r"/*": {"origins": "*"}})
-
-
-@app.route('/', methods=['GET'])
-def index():
-    return render_template('index.html')
-
-
-@app.route('/speech-to-text', methods=['POST'])
-def speech_to_text_route():
-    print("processing speech-to-text")
-    audio_binary = request.data # Get the user's speech from their request
-    text = speech_to_text(audio_binary) # Call speech_to_text function to transcribe the speech
-
-    # Return the response back to the user in JSON format
-    response = app.response_class(
-        response=json.dumps({'text': text}),
-        status=200,
-        mimetype='application/json'
-    )
-    print(response)
-    print(response.data)
-    return response
-
-
-@app.route('/process-message', methods=['POST'])
-def process_message_route():
-    user_message = request.json['userMessage'] # Get user's message from their request
-    print('user_message', user_message)
-
-    voice = request.json['voice'] # Get user's preferred voice from their request
-    print('voice', voice)
-
-    # Call openai_process_message function to process the user's message and get a response back
-    openai_response_text = openai_process_message(user_message)
-
-    # Clean the response to remove any emptylines
-    openai_response_text = os.linesep.join([s for s in openai_response_text.splitlines() if s])
-
-    # Call our text_to_speech function to convert OpenAI Api's reponse to speech
-    openai_response_speech = text_to_speech(openai_response_text, voice)
-
-    # convert openai_response_speech to base64 string so it can be sent back in the JSON response
-    openai_response_speech = base64.b64encode(openai_response_speech).decode('utf-8')
-
-    # Send a JSON response back to the user containing their message's response both in text and speech formats
-    response = app.response_class(
-        response=json.dumps({"openaiResponseText": openai_response_text, "openaiResponseSpeech": openai_response_speech}),
-        status=200,
-        mimetype='application/json'
-    )
-
-    print(response)
-    return response
-
-
-if __name__ == "__main__":
-    app.run(port=8000, host='0.0.0.0')
+import torch
+from transformers import pipeline
+
+# Initialize the speech-to-text pipeline from Hugging Face Transformers
+# This uses the "openai/whisper-tiny.en" model for automatic speech recognition (ASR)
+# The `chunk_length_s` parameter specifies the chunk length in seconds for processing
+pipe = pipeline(
+  "automatic-speech-recognition",
+  model="openai/whisper-tiny.en",
+  chunk_length_s=30,
+)
+
+# Define the path to the audio file that needs to be transcribed
+sample = 'downloaded_audio.mp3'
+
+# Perform speech recognition on the audio file
+# The `batch_size=8` parameter indicates how many chunks are processed at a time
+# The result is stored in `prediction` with the key "text" containing the transcribed text
+prediction = pipe(sample, batch_size=8)["text"]
+
+# Print the transcribed text to the console
+print(prediction)