Update app.py
Browse files
app.py
CHANGED
@@ -11,6 +11,7 @@ from pydub import AudioSegment
|
|
11 |
import requests
|
12 |
import mimetypes
|
13 |
import urllib.parse
|
|
|
14 |
|
15 |
# Configure logging
|
16 |
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
|
@@ -18,7 +19,7 @@ logger = logging.getLogger(__name__)
|
|
18 |
|
19 |
# Try to import moviepy with the simpler import statement
|
20 |
try:
|
21 |
-
from moviepy import VideoFileClip
|
22 |
logger.info("MoviePy (VideoFileClip) successfully imported")
|
23 |
except ImportError as e:
|
24 |
logger.error(f"Error importing MoviePy (VideoFileClip): {str(e)}")
|
@@ -92,6 +93,15 @@ def transcribe_audio_chunks(chunks):
|
|
92 |
transcriptions.append(transcript.get('text', ''))
|
93 |
return ' '.join(transcriptions)
|
94 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
95 |
def process_media(file_path, is_url=False):
|
96 |
global generated_file, transcription_text
|
97 |
temp_file = None
|
@@ -100,43 +110,27 @@ def process_media(file_path, is_url=False):
|
|
100 |
if is_url:
|
101 |
logger.info(f"Processing URL: {file_path}")
|
102 |
try:
|
103 |
-
|
104 |
-
|
105 |
-
content_type = response.headers.get('content-type', '')
|
106 |
-
extension = mimetypes.guess_extension(content_type) or ''
|
107 |
-
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=extension)
|
108 |
-
for chunk in response.iter_content(chunk_size=8192):
|
109 |
-
temp_file.write(chunk)
|
110 |
-
temp_file.close()
|
111 |
-
logger.info(f"URL content downloaded: {temp_file.name}")
|
112 |
except Exception as e:
|
113 |
logger.error(f"Error downloading URL content: {str(e)}")
|
114 |
return f"Error downloading URL content: {str(e)}", False
|
115 |
else:
|
116 |
logger.info("Processing uploaded file")
|
117 |
-
temp_file = tempfile.NamedTemporaryFile(delete=False)
|
118 |
temp_file.write(file_path)
|
119 |
temp_file.close()
|
120 |
-
|
|
|
121 |
|
122 |
-
#
|
|
|
123 |
try:
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
-
logger.warning(f"Could not process with moviepy: {str(e)}")
|
130 |
-
# If moviepy fails, try with pydub
|
131 |
-
try:
|
132 |
-
audio = AudioSegment.from_file(temp_file.name)
|
133 |
-
wav_path = temp_file.name + ".wav"
|
134 |
-
audio.export(wav_path, format="wav")
|
135 |
-
except Exception as e:
|
136 |
-
logger.error(f"Could not process audio: {str(e)}")
|
137 |
-
return f"Could not process audio: {str(e)}", False
|
138 |
-
|
139 |
-
logger.info(f"Audio extracted to WAV: {wav_path}")
|
140 |
|
141 |
# Chunk the audio file
|
142 |
audio = AudioSegment.from_wav(wav_path)
|
@@ -156,8 +150,8 @@ def process_media(file_path, is_url=False):
|
|
156 |
logger.error(f"Error during processing: {str(e)}")
|
157 |
return f"An error occurred: {str(e)}", False
|
158 |
finally:
|
159 |
-
if temp_file and os.path.exists(temp_file
|
160 |
-
os.unlink(temp_file
|
161 |
if wav_path and os.path.exists(wav_path):
|
162 |
os.unlink(wav_path)
|
163 |
|
|
|
11 |
import requests
|
12 |
import mimetypes
|
13 |
import urllib.parse
|
14 |
+
import subprocess
|
15 |
|
16 |
# Configure logging
|
17 |
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
|
|
|
19 |
|
20 |
# Try to import moviepy with the simpler import statement
|
21 |
try:
|
22 |
+
from moviepy import VideoFileClip, AudioFileClip
|
23 |
logger.info("MoviePy (VideoFileClip) successfully imported")
|
24 |
except ImportError as e:
|
25 |
logger.error(f"Error importing MoviePy (VideoFileClip): {str(e)}")
|
|
|
93 |
transcriptions.append(transcript.get('text', ''))
|
94 |
return ' '.join(transcriptions)
|
95 |
|
96 |
+
def download_file(url):
|
97 |
+
local_filename = url.split('/')[-1]
|
98 |
+
with requests.get(url, stream=True) as r:
|
99 |
+
r.raise_for_status()
|
100 |
+
with open(local_filename, 'wb') as f:
|
101 |
+
for chunk in r.iter_content(chunk_size=8192):
|
102 |
+
f.write(chunk)
|
103 |
+
return local_filename
|
104 |
+
|
105 |
def process_media(file_path, is_url=False):
|
106 |
global generated_file, transcription_text
|
107 |
temp_file = None
|
|
|
110 |
if is_url:
|
111 |
logger.info(f"Processing URL: {file_path}")
|
112 |
try:
|
113 |
+
temp_file = download_file(file_path)
|
114 |
+
logger.info(f"URL content downloaded: {temp_file}")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
115 |
except Exception as e:
|
116 |
logger.error(f"Error downloading URL content: {str(e)}")
|
117 |
return f"Error downloading URL content: {str(e)}", False
|
118 |
else:
|
119 |
logger.info("Processing uploaded file")
|
120 |
+
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp4')
|
121 |
temp_file.write(file_path)
|
122 |
temp_file.close()
|
123 |
+
temp_file = temp_file.name
|
124 |
+
logger.info(f"Uploaded file saved: {temp_file}")
|
125 |
|
126 |
+
# Convert to WAV using ffmpeg
|
127 |
+
wav_path = temp_file + ".wav"
|
128 |
try:
|
129 |
+
subprocess.run(['ffmpeg', '-i', temp_file, '-acodec', 'pcm_s16le', '-ar', '44100', wav_path], check=True)
|
130 |
+
logger.info(f"Audio extracted to WAV: {wav_path}")
|
131 |
+
except subprocess.CalledProcessError as e:
|
132 |
+
logger.error(f"FFmpeg conversion failed: {str(e)}")
|
133 |
+
return f"FFmpeg conversion failed: {str(e)}", False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
|
135 |
# Chunk the audio file
|
136 |
audio = AudioSegment.from_wav(wav_path)
|
|
|
150 |
logger.error(f"Error during processing: {str(e)}")
|
151 |
return f"An error occurred: {str(e)}", False
|
152 |
finally:
|
153 |
+
if temp_file and os.path.exists(temp_file):
|
154 |
+
os.unlink(temp_file)
|
155 |
if wav_path and os.path.exists(wav_path):
|
156 |
os.unlink(wav_path)
|
157 |
|