Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.19902 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918177104986112 |
|---|---|
| author | Zhang, Binbin Liang, Chengdong Wang, Shuai Geng, Xuelong Guo, Zhao Li, Haoyu Yin, Hao Yang, Xipeng Zhang, Pengshen Ma, Changwei Xie, Lei |
| author_facet | Zhang, Binbin Liang, Chengdong Wang, Shuai Geng, Xuelong Guo, Zhao Li, Haoyu Yin, Hao Yang, Xipeng Zhang, Pengshen Ma, Changwei Xie, Lei |
| contents | In this paper, we present WEST(WE Speech Toolkit), a speech toolkit based on a large language model (LLM) for speech understanding, generation, and interaction. There are three key features of WEST: 1) Fully LLM-based: Standing on the shoulders of giants by reusing mature architectures, ecosystems (e.g., Hugging Face), and methods (e.g., sequence packing) from large models. 2) Full-stack: Supports tasks such as recognition, synthesis, understanding, dialogue, and multimodal capabilities, with extensibility to incorporate open-source models. 3) Simple and Stupid: A simple and stupid speech toolkit that everyone can Touch. In addition, WEST provides two types of recipes, models, and experimental results. The first is entirely based on open-source models and open-source data, allowing users to fully reproduce the experiments in this paper and serving as a verification system or minimal system baseline. The second is trained on massive data, offering superior performance so the user can directly apply it out of the box. WEST is publicly avilable at https://github.com/wenet-e2e/west/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19902 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WEST: LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction Zhang, Binbin Liang, Chengdong Wang, Shuai Geng, Xuelong Guo, Zhao Li, Haoyu Yin, Hao Yang, Xipeng Zhang, Pengshen Ma, Changwei Xie, Lei Computation and Language In this paper, we present WEST(WE Speech Toolkit), a speech toolkit based on a large language model (LLM) for speech understanding, generation, and interaction. There are three key features of WEST: 1) Fully LLM-based: Standing on the shoulders of giants by reusing mature architectures, ecosystems (e.g., Hugging Face), and methods (e.g., sequence packing) from large models. 2) Full-stack: Supports tasks such as recognition, synthesis, understanding, dialogue, and multimodal capabilities, with extensibility to incorporate open-source models. 3) Simple and Stupid: A simple and stupid speech toolkit that everyone can Touch. In addition, WEST provides two types of recipes, models, and experimental results. The first is entirely based on open-source models and open-source data, allowing users to fully reproduce the experiments in this paper and serving as a verification system or minimal system baseline. The second is trained on massive data, offering superior performance so the user can directly apply it out of the box. WEST is publicly avilable at https://github.com/wenet-e2e/west/ |
| title | WEST: LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.19902 |