Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.00291 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908474568343552 |
|---|---|
| author | Pham, Linh |
| author_facet | Pham, Linh |
| contents | There are few code switching datasets, labeled or unlabled, that exist today. As a result, ASR requires new methods to utilize the vast monolingual data and models that exist. This paper uses OpenAI's open source ASR model, Whisper, which has been pre-trained on 680K hours of audio to perform monolingual ASR tasks. In Part 1, this paper examines how exploiting Whisper's monolingual ability to individually tokenize training text, called "Switching Tokenizers Method", improves transcription accuracy. In Part 2, we combine the Switching Tokenizers Method from part 1 and train a GELU based adapter on the encoder. These two methods reduced Total Mixed Error Rate (MER) to 9.4% for the ASCEND dataset, 6% for SEAME devman and 9.7% for SEAME devsge, outperforming current SoTA methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00291 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Code Switching with Supervised Fine Tuning and GELU Adapters Pham, Linh Sound Audio and Speech Processing There are few code switching datasets, labeled or unlabled, that exist today. As a result, ASR requires new methods to utilize the vast monolingual data and models that exist. This paper uses OpenAI's open source ASR model, Whisper, which has been pre-trained on 680K hours of audio to perform monolingual ASR tasks. In Part 1, this paper examines how exploiting Whisper's monolingual ability to individually tokenize training text, called "Switching Tokenizers Method", improves transcription accuracy. In Part 2, we combine the Switching Tokenizers Method from part 1 and train a GELU based adapter on the encoder. These two methods reduced Total Mixed Error Rate (MER) to 9.4% for the ASCEND dataset, 6% for SEAME devman and 9.7% for SEAME devsge, outperforming current SoTA methods. |
| title | Improving Code Switching with Supervised Fine Tuning and GELU Adapters |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.00291 |