Recent content by ironfevers

Nice prompt, thanks for sharing. I'll use it from now on. Seeing onee-san in a subtitle is new to me and I really like it. Onee-san sounds more endearing and immersive like in dass-546. Previously the word, sis, takes me out of the plot especially when it's just an older neighbor with no blood...

I took mei2's Colab code and made a FasterWhisperWithVAD_pro, also with checkpoint resume functionality. Sacrifices some quality for significantly faster speed. 4-5x faster than normal Whisper at similar beam_size. I find large-v2 gives better results overall on normal Whisper, but on Faster...

I can't open it. The file has been corrupted or is not a valid notebook file.

Yes both scripts will work. If you are not able to start the script, then you missed installing something. Ask Claude, Gemini, Perplexity or ChatGPT for installation help. Here are some quick instructions from ChatGPT: Check your python version python3 --version To install google chrome: sudo...

Having Python installed on your PC will save you so much time. I have lots of Python scripts to share. I have Python 3.10.11 installed for reference. My clean_japanese.py removes repetitions, cleans up moaning, deletes garbage lines and does replacements of mis-transcribed phrases with whatever...

Keep the audio file, json and partial filenames the same and it will load the partial srt tomorrow and continue appending to it. Or upload those files to a different Colab account and it will also continue.

Yup, the initial_prompt tells Whisper to transcribe everything even moans. You don't have to manually clean it. Use my clean_japanese.py. It will automatically clean all repetitions, moaning, laughing, and garbage.

Before it can only process one file then it will say out of memory error. Now it'll keep continuing after each file without out of memory errors.

I reuploaded it. See my edit.

Yes, all results are saved in the partial.srt and ckpt.json found inside /WhisperJAV. Don't move or edit those files as it's running.

I added checkpoint resume functionality to Mei2's WhisperWithVAD_pro Colab code. Download it in the Tutorials Whisper thread. I updated my clean_japanese.py. A lot more patterns have been added. It's very comprehensive now. I updated the SYS_MSG in my deepseek_srt.py. Now the translations have...

Gemini Pro helped me add checkpoint resume functionality to Mei2's WhisperWithVAD_pro Colab code. Now it saves a checkpoint file and partial srt periodically. Ever been frustrated when you reached the time limit and all progress is lost? If you crash from memory issues, reach the time limit...

I wanted to grab the Chinese subtitle for MFYD-001 but it never got made. Time to revisit Whisper. I didn't know about the PRO version until recently. Mei2 is awesome for making it. I wanted to improve my workflow and so I made a Python script for cleaning the Japanese srt. Garbage lines of...

With an extra step of restart session, you can avoid the "numpy.dtype size changed" error without needing to upgrade those packages. The workflow is mount Google Drive, setup, click runtime>restart session, set parameters, then run Whisper. In WhisperPro, I use an initial_prompt =...

Just learned about this. Use the new model for improved translations. Change from MODEL = "accounts/fireworks/models/deepseek-v3" to MODEL = "accounts/fireworks/models/deepseek-v3-0324". My first run caused line merges at TEMPERATURE = 0.9. My new recommended default is TEMPERATURE = 0.8 Nao...