import requests import pytz import streamlit as st from datetime import datetime from streamlit_audio_recorder import AudioRecorder API_URL = "https://tonpixzfvq3791u9.us-east-1.aws.endpoints.huggingface.cloud" key = 'test-public-anonymous-T4-Whisper-Small-En' headers = { "Authorization": "Bearer {key}", "Content-Type": "audio/wav" } def generate_filename(prompt, file_type): central = pytz.timezone('US/Central') safe_date_time = datetime.now(central).strftime("%m%d_%H%M") replaced_prompt = prompt.replace(" ", "_").replace("\n", "_") safe_prompt = "".join(x for x in replaced_prompt if x.isalnum() or x == "_")[:90] return f"{safe_date_time}_{safe_prompt}.{file_type}" def query(filename): with open(filename, "rb") as f: data = f.read() response = requests.post(API_URL, headers=headers, data=data) return response.json() def save_and_play_audio(audio_recorder): audio_bytes = audio_recorder.get_audio() if audio_bytes: filename = generate_filename("Recording", "wav") with open(filename, 'wb') as f: f.write(audio_bytes) st.audio(audio_bytes, format="audio/wav") return filename return None st.title("Speech to Text") st.write("Record your speech and get the text.") audio_recorder = AudioRecorder() audio_recorder.start() if st.button("Stop recording"): audio_recorder.stop() filename = save_and_play_audio(audio_recorder) if filename: output = query(filename) st.write("Transcription:") st.write(output)