include latest model

README.md

@@ -25,7 +25,9 @@ We host several models, which are specifically tailored to the processing of Fle
 
 ### Automatic Speech Recognition (ASR)
 
--- **ASR_subtitles_v2** (Recommended): The second version of our Automatic Speech Recognition and Subtitle Generation model, with improved architecture and trained on 14000 hours of Flemish broadcast subtitled speech data. 
+-- **NeLF_S2T_Pytorch** (Recommended): The third version of our Automatic Speech Recognition and Subtitle Generation model. It is a fine-tuned version of ASR_subtitles_v2 without Kaldi-dependency (pure Pytorch), and refined training data leveraging contextualisation techniques for pseudo-labeling.
+
+-- **ASR_subtitles_v2**: The second version of our Automatic Speech Recognition and Subtitle Generation model, with improved architecture and trained on 14000 hours of Flemish broadcast subtitled speech data. 
 It can generate both an exact verbatim transcription with annotation tags as well as a fully formatted and cleaned up subtitle transcription.
 
 -- **ASR_subtitles_v2_small**: Smaller variant of ASR_subtitles_v2 with almost as good performance.
@@ -49,7 +51,8 @@ Word Error Rates on different test sets.
 
 |Model Tag|Number of Parameters|Test CGN|Test Media|
 |:---|:---:|:---:|:---:|
-|ASR_subtitles_v2|180M|**6.49**|**8.63**|
+|NeLF_S2T_Pytorch|180M|6.65|8.23|
+|ASR_subtitles_v2|180M|6.49|8.63|
 |ASR_subtitles_v2_small|70M|6.93|9.30|
 |Whisper large finetuned|1550M|7.83|10.64|
 |Whisper large v3|1550M|11.54|13.76|