from transformers import pipeline
import librosa
import soundfile as sf
import matplotlib.pyplot as plt
import numpy as np
import requests
from io import BytesIO

# Initialize the automatic speech recognition pipeline
transcriber = pipeline("automatic-speech-recognition")

# Download an audio sample
audio_url = "https://github.com/librosa/librosa/raw/main/tests/data/choice.wav"
response = requests.get(audio_url)
with open("speech_sample.wav", "wb") as f:
    f.write(response.content)

# Load the audio
audio, sr = librosa.load("speech_sample.wav", sr=16000)

# Visualize the waveform
plt.figure(figsize=(10, 4))
plt.plot(np.linspace(0, len(audio)/sr, len(audio)), audio)
plt.title("Audio Waveform")
plt.xlabel("Time (s)")
plt.ylabel("Amplitude")
plt.tight_layout()
plt.show()

# Transcribe audio
result = transcriber("speech_sample.wav")
print(f"Transcription: {result['text']}")
Copy