Spaces:
Sleeping
Sleeping
File size: 4,094 Bytes
4a9476d 38a10c9 7cad919 38a10c9 7cad919 4a9476d 7cad919 4a9476d a068717 4a9476d a068717 4a9476d e7b9dd8 4a9476d e7b9dd8 4a9476d a068717 4a9476d |
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 |
import os
import tempfile
import subprocess
import streamlit as st
from pydub import AudioSegment
import shutil
AudioSegment.converter = shutil.which("ffmpeg")
# -------------------------------
# Utility Function: Download audio from a Video url
# -------------------------------
def download_audio_as_wav(url, max_filesize_mb=70):
"""
Downloads audio from a URL using yt-dlp, then converts it to WAV using ffmpeg.
Supports fallback formats (.m4a, .webm, .opus) if .mp3 not found.
Cleans up temporary files after use.
Returns path to .wav file or None on failure.
"""
audio_path = None
temp_wav = None
try:
with tempfile.TemporaryDirectory() as temp_dir:
max_bytes = max_filesize_mb * 1024 * 1024
output_template = os.path.join(temp_dir, "audio.%(ext)s")
cookies_b64 = os.getenv("cookies")
if not cookies_b64:
raise EnvironmentError("cookies environment variable not set.")
# Decode and write cookies.txt
with open(temp_cookie_path, "wb") as f:
f.write(base64.b64decode(cookies_b64))
# yt-dlp download command
download_cmd = [
"yt-dlp",
"-f", f"bestaudio[filesize<={max_bytes}]",
"--extract-audio",
"--audio-format", "mp3",
"--no-playlist",
"--no-cache-dir",
"--restrict-filenames",
"--cookies", temp_cookie_path,
"-o", output_template,
url
]
subprocess.run(download_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, check=True)
# Try to locate audio file (mp3 or fallback)
common_exts = [".mp3", ".m4a", ".webm", ".opus"]
for ext in common_exts:
matches = [f for f in os.listdir(temp_dir) if f.endswith(ext)]
if matches:
audio_path = os.path.join(temp_dir, matches[0])
break
if not audio_path or not os.path.exists(audio_path):
st.error("No supported audio file found after download.")
return None
# Convert to WAV (outside temp_dir so it persists)
temp_wav = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
convert_cmd = ["ffmpeg", "-y", "-i", audio_path, temp_wav.name]
subprocess.run(convert_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, check=True)
# Return WAV file path; temp_dir and downloaded audio cleaned automatically
return temp_wav.name
except subprocess.CalledProcessError as e:
error_msg = e.stderr.decode() if hasattr(e, "stderr") else str(e)
if "st" in globals():
st.error("Audio download or conversion failed.")
st.code(error_msg)
else:
print("Error during processing:", error_msg)
# Cleanup wav if created
if temp_wav is not None and os.path.exists(temp_wav.name):
os.remove(temp_wav.name)
st.stop()
return None
# --------------------------
# Utility: Trim audios to 2 minutes
# --------------------------
def trim_audio(input_wav_path, max_duration_sec=120):
"""
Trims the input .wav file to the first `max_duration_sec` seconds.
Returns the path to the trimmed .wav file.
"""
try:
# Load audio using pydub
audio = AudioSegment.from_wav(input_wav_path)
# Trim to max_duration_sec
trimmed_audio = audio[:max_duration_sec * 1000] # pydub uses milliseconds
# Save to a new temporary .wav file
trimmed_file = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
trimmed_audio.export(trimmed_file.name, format="wav")
return trimmed_file.name
except Exception as e:
st.error(f"Error trimming audio: {e}")
if trimmed_file and os.path.exists(trimmed_file.name):
os.remove(trimmed_file.name)
return None
|