Spaces:
Sleeping
Sleeping
File size: 9,754 Bytes
70b9e48 98851f3 e50410b 70b9e48 82467b2 70b9e48 e50410b 70b9e48 e50410b 575bce9 e50410b 575bce9 3e2d79c 575bce9 3e2d79c 8974aa3 3e2d79c 98851f3 3e2d79c 98851f3 3e2d79c 8974aa3 3e2d79c 98851f3 3e2d79c 98851f3 3e2d79c 98851f3 3e2d79c 98851f3 e50410b 98851f3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
import streamlit as st
import moviepy.editor as mp
import speech_recognition as sr
from pydub import AudioSegment
import tempfile
import os
import io
from pytube import YouTube
import requests
# 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."
# Function to download audio from YouTube and convert it to WAV
def download_youtube_audio(url):
# Get the YouTube video
yt = YouTube(url)
# Get the highest quality stream available (audio only)
audio_stream = yt.streams.filter(only_audio=True).first()
# Download the audio as an MP4 file (audio-only)
temp_audio_path = tempfile.mktemp(suffix=".mp4")
audio_stream.download(output_path=temp_audio_path)
# Convert the downloaded MP4 to WAV format
wav_audio_file = convert_mp3_to_wav(temp_audio_path)
# Cleanup the temporary MP4 file
os.remove(temp_audio_path)
return wav_audio_file
# Streamlit app layout
st.title("Video, Audio, and YouTube to Text Transcription")
st.write("Upload a video, audio file, or provide a YouTube URL to convert it to transcription.")
# Create tabs to separate video, audio, and YouTube URL uploads
tab = st.selectbox("Select the type of file to upload", ["Video", "Audio", "YouTube URL"])
if tab == "Video":
# 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)
# Store transcription and audio file in session state
st.session_state.transcription = transcription
# Store the audio file as a BytesIO object in memory
with open(wav_audio_file, "rb") as f:
audio_data = f.read()
st.session_state.wav_audio_file = io.BytesIO(audio_data)
# Cleanup temporary files
os.remove(tmp_video_path)
os.remove(audio_file)
# Check if transcription and audio file are stored in session state
if 'transcription' in st.session_state and 'wav_audio_file' in st.session_state:
# Provide the audio file to the user for download
st.audio(st.session_state.wav_audio_file, format='audio/wav')
# Add download buttons for the transcription and audio
# Downloadable transcription file
st.download_button(
label="Download Transcription",
data=st.session_state.transcription,
file_name="transcription.txt",
mime="text/plain"
)
# Downloadable audio file
st.download_button(
label="Download Audio",
data=st.session_state.wav_audio_file,
file_name="converted_audio.wav",
mime="audio/wav"
)
elif tab == "Audio":
# File uploader for audio
uploaded_audio = st.file_uploader("Upload Audio", type=["wav", "mp3"])
if uploaded_audio is not None:
# Save the uploaded audio file temporarily
with tempfile.NamedTemporaryFile(delete=False) as tmp_audio:
tmp_audio.write(uploaded_audio.read())
tmp_audio_path = tmp_audio.name
# Add an "Analyze Audio" button
if st.button("Analyze Audio"):
with st.spinner("Processing audio... Please wait."):
# Convert audio to WAV if it's in MP3 format
if uploaded_audio.type == "audio/mpeg":
wav_audio_file = convert_mp3_to_wav(tmp_audio_path)
else:
wav_audio_file = tmp_audio_path
# Transcribe audio to text
transcription = transcribe_audio(wav_audio_file)
# Show the transcription
st.text_area("Transcription", transcription, height=300)
# Store transcription in session state
st.session_state.transcription_audio = transcription
# Store the audio file as a BytesIO object in memory
with open(wav_audio_file, "rb") as f:
audio_data = f.read()
st.session_state.wav_audio_file_audio = io.BytesIO(audio_data)
# Cleanup temporary audio file
os.remove(tmp_audio_path)
# Check if transcription and audio file are stored in session state
if 'transcription_audio' in st.session_state and 'wav_audio_file_audio' in st.session_state:
# Provide the audio file to the user for download
st.audio(st.session_state.wav_audio_file_audio, format='audio/wav')
# Add download buttons for the transcription and audio
# Downloadable transcription file
st.download_button(
label="Download Transcription",
data=st.session_state.transcription_audio,
file_name="transcription_audio.txt",
mime="text/plain"
)
# Downloadable audio file
st.download_button(
label="Download Audio",
data=st.session_state.wav_audio_file_audio,
file_name="converted_audio_audio.wav",
mime="audio/wav"
)
elif tab == "YouTube URL":
# Input for YouTube URL
youtube_url = st.text_input("Enter YouTube URL")
if youtube_url:
# Add an "Analyze YouTube URL" button
if st.button("Analyze YouTube URL"):
with st.spinner("Processing YouTube video... Please wait."):
try:
# Download audio from the YouTube video
wav_audio_file = download_youtube_audio(youtube_url)
# Transcribe audio to text
transcription = transcribe_audio(wav_audio_file)
# Show the transcription
st.text_area("Transcription", transcription, height=300)
# Store transcription and audio file in session state
st.session_state.transcription_youtube = transcription
# Store the audio file as a BytesIO object in memory
with open(wav_audio_file, "rb") as f:
audio_data = f.read()
st.session_state.wav_audio_file_youtube = io.BytesIO(audio_data)
# Cleanup the temporary audio file
os.remove(wav_audio_file)
except Exception as e:
st.error(f"Error processing the YouTube URL: {e}")
# Check if transcription and audio file are stored in session state
if 'transcription_youtube' in st.session_state and 'wav_audio_file_youtube' in st.session_state:
# Provide the audio file to the user for download
st.audio(st.session_state.wav_audio_file_youtube, format='audio/wav')
# Add download buttons for the transcription and audio
# Downloadable transcription file
st.download_button(
label="Download Transcription",
data=st.session_state.transcription_youtube,
file_name="transcription_youtube.txt",
mime="text/plain"
)
# Downloadable audio file
st.download_button(
label="Download Audio",
data=st.session_state.wav_audio_file_youtube,
file_name="converted_audio_youtube.wav",
mime="audio/wav"
) |