Spaces:
Sleeping
Sleeping
Upload 2 files
Browse files- app.py +86 -0
- requirements.txt +6 -0
app.py
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
import gradio as gr
|
| 3 |
+
import pandas as pd
|
| 4 |
+
import requests
|
| 5 |
+
import io
|
| 6 |
+
import zipfile
|
| 7 |
+
from pydub import AudioSegment
|
| 8 |
+
|
| 9 |
+
def process_csv(file):
|
| 10 |
+
# Read CSV
|
| 11 |
+
df = pd.read_csv(file.name)
|
| 12 |
+
|
| 13 |
+
results = []
|
| 14 |
+
errors = []
|
| 15 |
+
|
| 16 |
+
# Process each audio link
|
| 17 |
+
for _, row in df.iterrows():
|
| 18 |
+
recorder_id = row.get("Fullname")
|
| 19 |
+
audio_url = row.get("Audio_Link")
|
| 20 |
+
|
| 21 |
+
if pd.isna(audio_url):
|
| 22 |
+
continue
|
| 23 |
+
|
| 24 |
+
try:
|
| 25 |
+
response = requests.get(audio_url, stream=True, timeout=30)
|
| 26 |
+
if response.status_code == 200:
|
| 27 |
+
audio_file = io.BytesIO(response.content)
|
| 28 |
+
audio = AudioSegment.from_file(audio_file)
|
| 29 |
+
duration_sec = len(audio) / 1000.0
|
| 30 |
+
duration_min = duration_sec / 60.0
|
| 31 |
+
|
| 32 |
+
results.append({
|
| 33 |
+
"recorder_id": recorder_id,
|
| 34 |
+
"audio_url": audio_url,
|
| 35 |
+
"duration_seconds": round(duration_sec, 2),
|
| 36 |
+
"duration_minutes": round(duration_min, 2)
|
| 37 |
+
})
|
| 38 |
+
else:
|
| 39 |
+
errors.append((recorder_id, audio_url, "Download failed"))
|
| 40 |
+
except Exception as e:
|
| 41 |
+
errors.append((recorder_id, audio_url, str(e)))
|
| 42 |
+
|
| 43 |
+
# Save results
|
| 44 |
+
output_df = pd.DataFrame(results)
|
| 45 |
+
output_filename = "audio_durations.csv"
|
| 46 |
+
output_df.to_csv(output_filename, index=False)
|
| 47 |
+
|
| 48 |
+
totals_df = output_df.groupby("recorder_id")[ "duration_minutes"].sum().reset_index()
|
| 49 |
+
totals_df.rename(columns={"duration_minutes": "total_minutes"}, inplace=True)
|
| 50 |
+
totals_filename = "total_durations_per_recorder.csv"
|
| 51 |
+
totals_df.to_csv(totals_filename, index=False)
|
| 52 |
+
|
| 53 |
+
error_filename = None
|
| 54 |
+
if errors:
|
| 55 |
+
error_df = pd.DataFrame(errors, columns=["recorder_id", "audio_url", "error"])
|
| 56 |
+
error_filename = "audio_errors.csv"
|
| 57 |
+
error_df.to_csv(error_filename, index=False)
|
| 58 |
+
|
| 59 |
+
# Create ZIP with results
|
| 60 |
+
zip_filename = "results.zip"
|
| 61 |
+
with zipfile.ZipFile(zip_filename, "w") as zipf:
|
| 62 |
+
zipf.write(output_filename)
|
| 63 |
+
zipf.write(totals_filename)
|
| 64 |
+
if error_filename:
|
| 65 |
+
zipf.write(error_filename)
|
| 66 |
+
|
| 67 |
+
return zip_filename
|
| 68 |
+
|
| 69 |
+
# Gradio UI
|
| 70 |
+
title = "Audio Duration Calculator"
|
| 71 |
+
description = """
|
| 72 |
+
Upload your CSV with 'Fullname' and 'Audio_Link' columns.
|
| 73 |
+
The app will calculate audio durations, total durations per recorder, and create error logs if needed.
|
| 74 |
+
You'll get a downloadable ZIP file.
|
| 75 |
+
"""
|
| 76 |
+
|
| 77 |
+
demo = gr.Interface(
|
| 78 |
+
fn=process_csv,
|
| 79 |
+
inputs=gr.File(label="Upload CSV", type="file"),
|
| 80 |
+
outputs=gr.File(label="Download Results ZIP"),
|
| 81 |
+
title=title,
|
| 82 |
+
description=description
|
| 83 |
+
)
|
| 84 |
+
|
| 85 |
+
if __name__ == "__main__":
|
| 86 |
+
demo.launch()
|
requirements.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
gradio
|
| 3 |
+
pandas
|
| 4 |
+
pydub
|
| 5 |
+
requests
|
| 6 |
+
ffmpeg
|