Spaces:
Paused
Paused
WIP
Browse files
app.py
CHANGED
@@ -270,11 +270,6 @@ def transcribe_youtube(url, return_timestamps, generate_subs, chunk_length_s=15,
|
|
270 |
logger.info(f"Transcription metadata: {metadata}")
|
271 |
logger.info(f"Transcription completed in {metadata.get('timing', {}).get('total_time', 0):.2f} seconds")
|
272 |
|
273 |
-
# Format response with segments (without id)
|
274 |
-
logger.info("Formatting response...")
|
275 |
-
formatted_result = result["transcription"]
|
276 |
-
logger.info(f"Formatted result contains {len(formatted_result['segments'])} segments")
|
277 |
-
|
278 |
# Generate subtitles if requested
|
279 |
srt_file = None
|
280 |
if generate_subs and return_timestamps and "segments" in result["transcription"]:
|
@@ -284,7 +279,7 @@ def transcribe_youtube(url, return_timestamps, generate_subs, chunk_length_s=15,
|
|
284 |
logger.info(f"Generated SRT file: {srt_file}")
|
285 |
|
286 |
logger.info("YouTube transcription process completed successfully")
|
287 |
-
return
|
288 |
|
289 |
except Exception as e:
|
290 |
logger.exception(f"Error in YouTube transcription: {str(e)}")
|
@@ -331,11 +326,6 @@ def transcribe(inputs, return_timestamps, generate_subs, chunk_length_s=15, batc
|
|
331 |
logger.info(f"Transcription metadata: {metadata}")
|
332 |
logger.info(f"Transcription completed in {metadata.get('timing', {}).get('total_time', 0):.2f} seconds")
|
333 |
|
334 |
-
# Format response with segments (without id)
|
335 |
-
logger.info("Formatting response...")
|
336 |
-
formatted_result = result["transcription"]
|
337 |
-
logger.info(f"Formatted result contains {len(formatted_result['segments'])} segments")
|
338 |
-
|
339 |
# Generate subtitles if requested
|
340 |
srt_file = None
|
341 |
if generate_subs and return_timestamps and "segments" in result["transcription"]:
|
@@ -345,7 +335,7 @@ def transcribe(inputs, return_timestamps, generate_subs, chunk_length_s=15, batc
|
|
345 |
logger.info(f"Generated SRT file: {srt_file}")
|
346 |
|
347 |
logger.info("Transcription process completed successfully")
|
348 |
-
return
|
349 |
|
350 |
except requests.exceptions.RequestException as e:
|
351 |
logger.exception(f"API request failed: {str(e)}")
|
@@ -368,9 +358,9 @@ youtube_transcribe = gr.Interface(
|
|
368 |
gr.Slider(minimum=8, maximum=128, value=8, step=8, label="Batch Size")
|
369 |
],
|
370 |
outputs=[
|
371 |
-
gr.JSON(label="
|
372 |
-
gr.JSON(label="Raw API Response", open=True),
|
373 |
gr.File(label="Subtitles (SRT)", visible=True),
|
|
|
374 |
],
|
375 |
title="Tajik Speech Transcription",
|
376 |
description=(
|
@@ -393,9 +383,9 @@ mf_transcribe = gr.Interface(
|
|
393 |
gr.Slider(minimum=8, maximum=128, value=8, step=8, label="Batch Size")
|
394 |
],
|
395 |
outputs=[
|
396 |
-
gr.JSON(label="
|
397 |
-
gr.JSON(label="Raw API Response", open=True),
|
398 |
gr.File(label="Subtitles (SRT)", visible=True),
|
|
|
399 |
],
|
400 |
title="Tajik Speech Transcription",
|
401 |
description=(
|
@@ -415,9 +405,9 @@ file_transcribe = gr.Interface(
|
|
415 |
gr.Slider(minimum=8, maximum=128, value=8, step=8, label="Batch Size")
|
416 |
],
|
417 |
outputs=[
|
418 |
-
gr.JSON(label="
|
419 |
-
gr.JSON(label="Raw API Response", open=True),
|
420 |
gr.File(label="Subtitles (SRT)", visible=True),
|
|
|
421 |
],
|
422 |
title="Tajik Speech Transcription",
|
423 |
description=(
|
|
|
270 |
logger.info(f"Transcription metadata: {metadata}")
|
271 |
logger.info(f"Transcription completed in {metadata.get('timing', {}).get('total_time', 0):.2f} seconds")
|
272 |
|
|
|
|
|
|
|
|
|
|
|
273 |
# Generate subtitles if requested
|
274 |
srt_file = None
|
275 |
if generate_subs and return_timestamps and "segments" in result["transcription"]:
|
|
|
279 |
logger.info(f"Generated SRT file: {srt_file}")
|
280 |
|
281 |
logger.info("YouTube transcription process completed successfully")
|
282 |
+
return result, srt_file, ""
|
283 |
|
284 |
except Exception as e:
|
285 |
logger.exception(f"Error in YouTube transcription: {str(e)}")
|
|
|
326 |
logger.info(f"Transcription metadata: {metadata}")
|
327 |
logger.info(f"Transcription completed in {metadata.get('timing', {}).get('total_time', 0):.2f} seconds")
|
328 |
|
|
|
|
|
|
|
|
|
|
|
329 |
# Generate subtitles if requested
|
330 |
srt_file = None
|
331 |
if generate_subs and return_timestamps and "segments" in result["transcription"]:
|
|
|
335 |
logger.info(f"Generated SRT file: {srt_file}")
|
336 |
|
337 |
logger.info("Transcription process completed successfully")
|
338 |
+
return result, srt_file, ""
|
339 |
|
340 |
except requests.exceptions.RequestException as e:
|
341 |
logger.exception(f"API request failed: {str(e)}")
|
|
|
358 |
gr.Slider(minimum=8, maximum=128, value=8, step=8, label="Batch Size")
|
359 |
],
|
360 |
outputs=[
|
361 |
+
gr.JSON(label="API Response", open=True),
|
|
|
362 |
gr.File(label="Subtitles (SRT)", visible=True),
|
363 |
+
gr.Textbox(label="Error", visible=False)
|
364 |
],
|
365 |
title="Tajik Speech Transcription",
|
366 |
description=(
|
|
|
383 |
gr.Slider(minimum=8, maximum=128, value=8, step=8, label="Batch Size")
|
384 |
],
|
385 |
outputs=[
|
386 |
+
gr.JSON(label="API Response", open=True),
|
|
|
387 |
gr.File(label="Subtitles (SRT)", visible=True),
|
388 |
+
gr.Textbox(label="Error", visible=False)
|
389 |
],
|
390 |
title="Tajik Speech Transcription",
|
391 |
description=(
|
|
|
405 |
gr.Slider(minimum=8, maximum=128, value=8, step=8, label="Batch Size")
|
406 |
],
|
407 |
outputs=[
|
408 |
+
gr.JSON(label="API Response", open=True),
|
|
|
409 |
gr.File(label="Subtitles (SRT)", visible=True),
|
410 |
+
gr.Textbox(label="Error", visible=False)
|
411 |
],
|
412 |
title="Tajik Speech Transcription",
|
413 |
description=(
|