Improved Open Source Automatic Subtitling for Lecture Videos
Code
Tasks
Datasets
LibriSpeech
Results from the Paper
Ranked #2 on
Speech Recognition
on TUDA
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Speech Recognition | TUDA | TDNN-HMM hybrid, FST (with RNNLM rescoring) | Test WER | 6.93% | # 2 |
Methods
No methods listed for this paper. Add
relevant methods here
