Patreon
Home / Videos / The New Best AI Subtitle Model? Canary Qwen 2.5B Tested Agai

The New Best AI Subtitle Model? Canary Qwen 2.5B Tested Against Whisper Large V3

ACE-Step XL 1.5 Premium remix tutorial: change lyrics and language, tune strength and melody retention, regenerate parts; a full remix takes about 33 seconds.

Published May 01, 2026 · 1,970 views · Watch on YouTube

Get the app and files

ACE-Step 1.5 Remix, Paints-Undo & Whisper Premium: Local AI Update

ACE-Step 1.5 Remix, Paints-Undo & Whisper Premium: Local AI Update

ACE-Step XL 1.5 Premium remix tutorial: change lyrics and language, tune strength and melody retention, regenerate parts; a full remix takes about 33 seconds.

Canary Qwen 2.5B vs Whisper: Open Source Subtitle Generator Full Guide

Canary Qwen 2.5B vs Whisper: Open Source Subtitle Generator Full Guide

Canary Qwen 2.5B in the Whisper-WebUI Premium app reached 5.91% WER and up to 46x real-time speed, ahead of Whisper Large V3 for English subtitles.

Chapters

  1. 0:00 Intro to the local open-source speech-to-text app and new Canary support
  2. 0:20 Quick demo setup with NVIDIA Canary Qwen 2.5B
  3. 0:33 Maximum-quality defaults and starting subtitle generation
  4. 0:48 Live transcription speed and accuracy preview
  5. 1:03 Chunk length settings for smaller or larger subtitle segments
  6. 1:18 Fast generation, supported exports, and restarting with all formats
  7. 1:31 Multiple subtitle file formats explained
  8. 1:47 Batch processing folders, output paths, subfolders, and overwrite mode
  9. 1:58 YouTube URLs, microphone/live transcription, translation, and BGM separation
  10. 2:09 Saving presets and using advanced parameters
  11. 2:24 Auto-optimized defaults for Whisper and Canary models
  12. 2:39 Canary Qwen 2.5B vs Whisper Large V3 comparison begins
  13. 2:54 Real-world WER benchmark and 5.91% Canary result
  14. 3:10 Why non-native English speech is harder to transcribe accurately
  15. 3:24 Canary speed advantage and 46x real-time transcription explained
  16. 3:43 Test averages across long and short tutorial videos
  17. 3:59 Cases where Whisper slightly wins and final Canary recommendation
  18. 4:14 Opening the output folder after transcription completes
  19. 4:27 VTT output, matching filenames, capitalization, and punctuation
  20. 4:44 Accuracy examples inside the generated transcript
  21. 4:58 TXT, TSV, SRT, LRC exports and word-level timestamp note
  22. 5:20 Download page, latest ZIP, and installation overview
  23. 5:31 Windows requirements: Python 3.11, Git, CUDA, and C++ notes
  24. 5:51 Choosing install location and keeping the app isolated in venv
  25. 6:04 Extracting the ZIP and running Windows install/update BAT
  26. 6:23 Automatic model downloads on first run
  27. 6:34 RunPod, Massed Compute, and Linux installation files
  28. 6:50 Where to learn RunPod and Massed Compute setup in the related guide
  29. 7:29 UV-powered Windows installation completes quickly
  30. 7:41 Starting the app with Windows start app BAT
  31. 7:58 Selecting video/audio input and generating subtitles on a fresh install
  32. 8:10 First-run Canary model download and 5GB model size
  33. 8:35 Easy setup goal and automatic fresh-install workflow
  34. 8:53 Discord, Patreon index, and 100+ SECourses applications
  35. 9:13 RTX 5000 support and updated NVIDIA driver requirement
  36. 9:35 Fresh-install transcription starts successfully
  37. 9:47 Automatic downloads for Canary, Whisper, diarization, and extra tools
  38. 10:16 Canary becomes the new default model recommendation
  39. 10:36 Subprocess mode to prevent VRAM and RAM leaks
  40. 10:51 Why running transcription as a subprocess is recommended
  41. 11:04 Switching back to Whisper models when needed
  42. 11:20 Whisper language coverage vs Canary and audio/video support
  43. 11:42 Real recording benchmark: 27 minutes transcribed in about 2 minutes
  44. 11:56 Model loading overhead and clean RAM/VRAM release
  45. 12:08 Final notes, subscribe reminder, and downloading the full transcript ZIP

About this video

NVIDIA NeMo Canary-Qwen-2.5B is an English speech recognition model that achieves state-of-the art performance on multiple English speech benchmarks. Canary model is the new king that dethroned famous Whisper.

Full tutorial for the Whisper TTS Premium speech-to-text app by SECourses with new NVIDIA Canary Qwen 2.5B support. In this video, I demo local subtitle generation, compare Canary Qwen 2.5B against Whisper Large V3, show output formats, batch processing, presets, YouTube URL and live microphone options, then install the app from scratch on Windows.

You will also see RunPod and Massed Compute notes, first-run model download, RTX 5000/CUDA 13 driver requirements, subprocess mode for preventing VRAM/RAM leaks, and when to use Whisper instead of Canary.

Links:

Download App and the source post: [ https://www.patreon.com/posts/whisper-webui-to-145395299 ]

Discord: [ https://discord.com/channels/772774097734074388/1079506787734134844 ]

Patreon app index: [ https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Patreon-Posts-Index.md ]

Related RunPod/Massed Compute setup tutorial: [ https://youtu.be/ZRrzvD4wNys ]

In my tutorial-video tests, Canary Qwen 2.5B achieved 5.91% global WER and reached up to 46x faster than real-time transcription, making it my new recommended default for English speech-to-text. Whisper remains useful when you need broader spoken-language support or word-level timestamps.

Chapters:

0:00 Intro to the local open-source speech-to-text app and new Canary support

0:20 Quick demo setup with NVIDIA Canary Qwen 2.5B

0:33 Maximum-quality defaults and starting subtitle generation

0:48 Live transcription speed and accuracy preview

1:03 Chunk length settings for smaller or larger subtitle segments

1:18 Fast generation, supported exports, and restarting with all formats

1:31 Multiple subtitle file formats explained

1:47 Batch processing folders, output paths, subfolders, and overwrite mode

1:58 YouTube URLs, microphone/live transcription, translation, and BGM separation

2:09 Saving presets and using advanced parameters

2:24 Auto-optimized defaults for Whisper and Canary models

2:39 Canary Qwen 2.5B vs Whisper Large V3 comparison begins

2:54 Real-world WER benchmark and 5.91% Canary result

3:10 Why non-native English speech is harder to transcribe accurately

3:24 Canary speed advantage and 46x real-time transcription explained

3:43 Test averages across long and short tutorial videos

3:59 Cases where Whisper slightly wins and final Canary recommendation

4:14 Opening the output folder after transcription completes

4:27 VTT output, matching filenames, capitalization, and punctuation

4:44 Accuracy examples inside the generated transcript

4:58 TXT, TSV, SRT, LRC exports and word-level timestamp note

5:20 Download page, latest ZIP, and installation overview

5:31 Windows requirements: Python 3.11, Git, CUDA, and C++ notes

5:51 Choosing install location and keeping the app isolated in venv

6:04 Extracting the ZIP and running Windows install/update BAT

6:23 Automatic model downloads on first run

6:34 RunPod, Massed Compute, and Linux installation files

6:50 Where to learn RunPod and Massed Compute setup in the related guide

7:29 UV-powered Windows installation completes quickly

7:41 Starting the app with Windows start app BAT