|
|
--- |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- ICTNLP/LongSpeech-Eval |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- accuracy |
|
|
base_model: |
|
|
- Qwen/Qwen2-Audio-7B-Instruct |
|
|
--- |
|
|
|
|
|
# The model for the paper '[FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing](https://arxiv.org/abs/2507.14815)' |
|
|
|
|
|
## Usage |
|
|
|
|
|
Please refer to [Github Page](https://github.com/ictnlp/FastLongSpeech) |
|
|
|
|
|
### Requirements |
|
|
|
|
|
We suggest to run with Python 3.10. |
|
|
Examples of usage: |
|
|
``` |
|
|
git clone https://github.com/ictnlp/FastLongSpeech.git |
|
|
cd transformers-main |
|
|
pip install -e . |
|
|
pip install deepspeed sentencepiece librosa |
|
|
``` |
|
|
|
|
|
## Evaluation Datasets |
|
|
- https://huggingface.co/datasets/ICTNLP/LongSpeech-Eval |
|
|
## Github Pages |
|
|
- https://github.com/ictnlp/FastLongSpeech |
|
|
|
