| language: | |
| - en | |
| license: cc-by-nc-4.0 | |
| tags: | |
| - prosody | |
| - speech | |
| - llm | |
| pipeline_tag: question-answering | |
| # SpeechCombine | |
| This repository contains the **model checkpoints, sample training data, and evaluation data** for | |
| the paper [Unlocking Speech鈥揟ext Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning] | |
| ## 馃搧 Repository structure | |
| - `Exps/`: SpeechCombine checkpoint and tokenizer | |
| - `eval/`: Eevaluation data and evaluator checkpoint | |
| - `tts/`: TTS checkpoint and speaker embedding | |
| - `training_data.jsonl`: SpeechCombine training data | |
| ## 馃敆 Citation | |
| If this resource is useful for your research, please consider citing our paper. | |
| --- | |
| License: CC BY-NC 4.0 |