translation.py

from google.cloud import speech
import wave
from pydub import AudioSegment

def get_audio_properties(file_path):
    """
    Get sample rate and number of channels from the WAV file.
    """
    with wave.open(file_path, "rb") as wav_file:
        sample_rate = wav_file.getframerate()
        channels = wav_file.getnchannels()
    return sample_rate, channels

def convert_to_mono(input_path, output_path):
    """Convert video from 2+ channel audio to 1 channel audio for a 
    single detection"""
    audio = AudioSegment.from_wav(input_path)
    mono_audio = audio.set_channels(1)
    mono_audio.export(output_path, format="wav")
    
def split_audio(file_path, chunk_length_ms=60000):  # 60 sec chunks
    audio = AudioSegment.from_wav(file_path)
    chunks = [audio[i:i + chunk_length_ms] for i in range(0, len(audio), chunk_length_ms)]

    chunk_files = []
    for i, chunk in enumerate(chunks):
        chunk_name = f"chunk_{i}.wav"
        chunk.export(chunk_name, format="wav")
        chunk_files.append(chunk_name)
    
    return chunk_files

def transcribe_audio(file_path):
    """Gets the .wav file path and perform speech to text
    returns the string witch represents the words spoken"""
    # Initialize the speech client
    client = speech.SpeechClient()

    # Get audio properties like sample rate and channels
    sample_rate, channels = get_audio_properties(file_path)

    # Open the audio file and read its content
    with open(file_path, "rb") as audio_file:
        audio_content = audio_file.read()

    # Prepare the audio content for transcription
    audio = speech.RecognitionAudio(content=audio_content)
    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=sample_rate,
        language_code="en-US",
        audio_channel_count=channels,
        enable_separate_recognition_per_channel=(channels > 1)
    )

    # Call the Google Cloud Speech API for recognition
    response = client.recognize(config=config, audio=audio)

    # Concatenate the transcripts from all results into one string
    concatenated_transcript = ". ".join([result.alternatives[0].transcript for result in response.results])

    # Return or print the concatenated transcript
    return concatenated_transcript

def get_transcription_from_sound(file_path:str)->str:
    """Converts the audio to a single channel and calls the transcription function"""
    output_path = "audio_mono.wav"
    convert_to_mono(file_path,output_path)
    
    final_transcript = transcribe_audio(output_path)
    
    return final_transcript

if __name__=="__main__":
    file_path = "jackhammer.wav"
    output_path = "audio_mono.wav"
    convert_to_mono(file_path,output_path)
    final_transcript = transcribe_audio(output_path)
    print(final_transcript)