From 5ebbf641f5374b793e4b39c9029f0b535a78658b Mon Sep 17 00:00:00 2001 From: Kurian Benoy Date: Thu, 29 Feb 2024 00:51:12 +0530 Subject: [PATCH 1/2] Update README.md --- README.md | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 12132bc..64c9362 100644 --- a/README.md +++ b/README.md @@ -215,8 +215,16 @@ Smaller chunks get very little context and becuase of this our model is sometime ![image](https://github.com/kurianbenoy/Indic-Subtitler/assets/24592806/d84082d5-6d1c-4ce5-8394-d749fbf6c8f7) -- Include more model families like faster-whisper, whisperX etc. -- Evaluate the performance of models in Indic subtitler on custom videos. +- Include more model families like faster-whisper, whisperX, vegam-Malayalam-whisper etc. + +![image](https://github.com/kurianbenoy/Indic-Subtitler/assets/24592806/57152204-c7df-4a0f-9cf7-105c8a60b666) + +![image](https://github.com/kurianbenoy/Indic-Subtitler/assets/24592806/77515f76-047a-4808-9c9f-67e838c29875) + + +- Evaluate the performance of models in Indic subtitler on custom videos. + +Made progress by adding ground truth to English audios ##### Few extra approaches to consider: @@ -230,9 +238,18 @@ Smaller chunks get very little context and becuase of this our model is sometime
-**Week 4 onwards 🌕** +**Week 4 🌕** - Evaluate the performance of Indic subtitler on various languages +- Audio quality enhancement with Demux + +https://github.com/kurianbenoy/Indic-Subtitler/issues/4 + +- Information page about best set of models and when to use it. + + +**Week 5 onwards 🌕** + - Fine-tune ASR models based on performance for respective languages and integrate even whisper-based audio models. - Build a desktop app similar to webapp for using all the functionalities From 6cd58c685cc2aa2cdc4a661f04ea043a010b6a1b Mon Sep 17 00:00:00 2001 From: kurianbenoy Date: Wed, 28 Feb 2024 20:48:50 +0530 Subject: [PATCH 2/2] update README --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 64c9362..27dd8ac 100644 --- a/README.md +++ b/README.md @@ -222,7 +222,7 @@ Smaller chunks get very little context and becuase of this our model is sometime ![image](https://github.com/kurianbenoy/Indic-Subtitler/assets/24592806/77515f76-047a-4808-9c9f-67e838c29875) -- Evaluate the performance of models in Indic subtitler on custom videos. +- Evaluate the performance of models in Indic subtitler on custom videos. Made progress by adding ground truth to English audios