Improve model card: Add Acknowledgement and Citation sections
#2
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -67,4 +67,26 @@ Following is the average word error rate (WER) evaluated on the [ESB datasets](h
|
|
| 67 |
| [lite-whisper-large-v3-turbo](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo) | 12.6 | 374M | 172M |
|
| 68 |
| [lite-whisper-large-v3-turbo-fast](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo-fast) | 20.1 | 313M | 172M |
|
| 69 |
| | | | |
|
| 70 |
-
| [whisper-medium](https://huggingface.co/openai/whisper-medium) | 14.8 | 306M | 457M |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
| [lite-whisper-large-v3-turbo](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo) | 12.6 | 374M | 172M |
|
| 68 |
| [lite-whisper-large-v3-turbo-fast](https://huggingface.co/efficient-speech/lite-whisper-large-v3-turbo-fast) | 20.1 | 313M | 172M |
|
| 69 |
| | | | |
|
| 70 |
+
| [whisper-medium](https://huggingface.co/openai/whisper-medium) | 14.8 | 306M | 457M |
|
| 71 |
+
|
| 72 |
+
## Acknowledgement
|
| 73 |
+
|
| 74 |
+
- [OpenAI Whisper](https://github.com/openai/whisper)
|
| 75 |
+
- [MLX Whisper](https://github.com/ml-explore/mlx-examples/tree/main/whisper)
|
| 76 |
+
- [ASR Leaderboard](https://github.com/huggingface/open_asr_leaderboard)
|
| 77 |
+
|
| 78 |
+
## Citation
|
| 79 |
+
|
| 80 |
+
If you use LiteASR in your research, please cite the following paper:
|
| 81 |
+
|
| 82 |
+
```
|
| 83 |
+
@misc{kamahori2025liteasrefficientautomaticspeech,
|
| 84 |
+
title={LiteASR: Efficient Automatic Speech Recognition and Low-Rank Approximation},
|
| 85 |
+
author={Keisuke Kamahori and Jungo Kasai and Noriyuki Kojima and Baris Kasikci},
|
| 86 |
+
year={2025},
|
| 87 |
+
eprint={2502.20583},
|
| 88 |
+
archivePrefix={arXiv},
|
| 89 |
+
primaryClass={cs.LG},
|
| 90 |
+
url={https://arxiv.org/abs/2502.20583},
|
| 91 |
+
}
|
| 92 |
+
```
|