| import openai | |
| import gradio as gr | |
| openai.api_key = "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" | |
| def transcribe(audio): | |
| with open(audio, "rb") as audio_file: | |
| transcript = openai.Audio.transcribe("whisper-1", audio_file) | |
| return transcript["text"] | |
| def generate_response(transcribed_text): | |
| response = openai.Completion.create( | |
| engine="text-davinci-003", | |
| prompt=transcribed_text, | |
| max_tokens=1024, | |
| n=1, | |
| stop=None, | |
| temperature=0.5, | |
| ) | |
| return response.choices[0].text | |
| def run_cmd(command): | |
| try: | |
| print(command) | |
| call(command) | |
| except KeyboardInterrupt: | |
| print("Process interrupted") | |
| sys.exit(1) | |
| def inference(text): | |
| cmd = ['tts', '--text', text] | |
| run_cmd(cmd) | |
| return 'tts_output.wav' | |
| def process_audio_and_respond(audio): | |
| text = transcribe(audio) | |
| response_text = generate_response(text) | |
| output_file = inference(response_text) | |
| return output_file | |
| demo = gr.Blocks() | |
| with demo: | |
| audio_file = gr.inputs.Audio(source="microphone", type="filepath") | |
| button = gr.Button("Uliza Swali") | |
| outputs = gr.outputs.Audio(type="filepath", label="Output Audio") | |
| button.click(fn=process_audio_and_respond, inputs=audio_file, outputs=outputs) | |
| demo.launch() | |