Spaces:
Sleeping
Sleeping
File size: 3,537 Bytes
70b9e48 82467b2 70b9e48 575bce9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
import streamlit as st
import moviepy.editor as mp
import speech_recognition as sr
from pydub import AudioSegment
import tempfile
import os
# Function to convert video to audio
def video_to_audio(video_file):
# Load the video using moviepy
video = mp.VideoFileClip(video_file)
# Extract audio
audio = video.audio
temp_audio_path = tempfile.mktemp(suffix=".mp3")
# Write the audio to a file
audio.write_audiofile(temp_audio_path)
return temp_audio_path
# Function to convert MP3 audio to WAV
def convert_mp3_to_wav(mp3_file):
# Load the MP3 file using pydub
audio = AudioSegment.from_mp3(mp3_file)
# Create a temporary WAV file
temp_wav_path = tempfile.mktemp(suffix=".wav")
# Export the audio to the temporary WAV file
audio.export(temp_wav_path, format="wav")
return temp_wav_path
# Function to transcribe audio to text
def transcribe_audio(audio_file):
# Initialize recognizer
recognizer = sr.Recognizer()
# Load the audio file using speech_recognition
audio = sr.AudioFile(audio_file)
with audio as source:
audio_data = recognizer.record(source)
try:
# Transcribe the audio data to text using Google Web Speech API
text = recognizer.recognize_google(audio_data)
return text
except sr.UnknownValueError:
return "Audio could not be understood."
except sr.RequestError:
return "Could not request results from Google Speech Recognition service."
# Streamlit app layout
st.title("Video to Audio to Text Transcription")
st.write("Upload a video file, and it will be converted to audio and transcribed into text.")
# File uploader for video
uploaded_video = st.file_uploader("Upload Video", type=["mp4", "mov", "avi"])
if uploaded_video is not None:
# Save the uploaded video file temporarily
with tempfile.NamedTemporaryFile(delete=False) as tmp_video:
tmp_video.write(uploaded_video.read())
tmp_video_path = tmp_video.name
# Add an "Analyze Video" button
if st.button("Analyze Video"):
with st.spinner("Processing video... Please wait."):
# Convert video to audio
audio_file = video_to_audio(tmp_video_path)
# Convert the extracted MP3 audio to WAV
wav_audio_file = convert_mp3_to_wav(audio_file)
# Transcribe audio to text
transcription = transcribe_audio(wav_audio_file)
# Show the transcription
st.text_area("Transcription", transcription, height=300)
# Provide the audio file to the user for download
st.audio(wav_audio_file, format="audio/wav")
# Add download buttons for the transcription and audio
# Downloadable transcription file
st.download_button(
label="Download Transcription",
data=transcription,
file_name="transcription.txt",
mime="text/plain"
)
# Downloadable audio file
with open(wav_audio_file, "rb") as audio_file_data:
st.download_button(
label="Download Audio",
data=audio_file_data,
file_name="converted_audio.wav",
mime="audio/wav"
)
# Cleanup temporary files
os.remove(tmp_video_path)
os.remove(audio_file)
os.remove(wav_audio_file)
|