From 32815db9b19ed4d77ad4c9eb4fd9605d1ec0073c Mon Sep 17 00:00:00 2001 From: McCloudS <64094529+McCloudS@users.noreply.github.com> Date: Sat, 10 Feb 2024 22:07:20 -0700 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 70aa3e0..4a5b39a 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@
Updates: -10 Feb 2024: Added some features from JaiZed's branch such as skipping if SDH subtitles are detected, functions updated to also be able to transcribe audio files, allow individual files to be manually transcribed, and a better implementation of forceLanguage. Added /batch endpoint (Thanks JaiZed). Allows you to navigate in a browser to http://subgen_ip:8090/docs and call the batch endpoint which can take a file or a folder to manually transcribe files. Added CLEAR_VRAM_ON_COMPLETE, HF_TRANSFORMERS, HF_BATCH_SIZE. Hugging Face Transformers boast '9x increase', but I have been unable to test them at this point. As of now, the Hugging Face Models will be re-downloaded on container restart, there is currently no function to set a save/download directory. Simplest work around is use the environment variable "HF_HUB_CACHE" and set it to "/subgen" for Docker. +10 Feb 2024: Added some features from JaiZed's branch such as skipping if SDH subtitles are detected, functions updated to also be able to transcribe audio files, allow individual files to be manually transcribed, and a better implementation of forceLanguage. Added /batch endpoint (Thanks JaiZed). Allows you to navigate in a browser to http://subgen_ip:8090/docs and call the batch endpoint which can take a file or a folder to manually transcribe files. Added CLEAR_VRAM_ON_COMPLETE, HF_TRANSFORMERS, HF_BATCH_SIZE. Hugging Face Transformers boast '9x increase', but my limited testing shows it's comparable to faster-whisper or slightly slower. I also have an older 8gb GPU. Simplest way to persist HF Transformer models is to set "HF_HUB_CACHE" and set it to "/subgen/models" for Docker (assuming you have the matching volume). 8 Feb 2024: Added FORCE_DETECTED_LANGUAGE_TO to force a wrongly detected language. Fixed asr to actually use the language passed to it.