FireRedTeam
/

FireRedASR-LLM-L

Automatic Speech Recognition

Model card Files Files and versions

FireRedTeam commited on Feb 17

Commit

6da4f1d

·

verified ·

1 Parent(s): 6ff2daf

Update README.md

Files changed (1) hide show

README.md +0 -2

README.md CHANGED Viewed

@@ -29,8 +29,6 @@ FireRedASR is designed to meet diverse requirements in superior performance and
 - FireRedASR-LLM: Designed to achieve state-of-the-art (SOTA) performance and to enable seamless end-to-end speech interaction. It adopts an Encoder-Adapter-LLM framework leveraging large language model (LLM) capabilities.
 - FireRedASR-AED: Designed to balance high performance and computational efficiency and to serve as an effective speech representation module in LLM-based speech models. It utilizes an Attention-based Encoder-Decoder (AED) architecture.
-![Model](/assets/FireRedASR_model.png)
 ## Evaluation
 Results are reported in Character Error Rate (CER%) for Chinese and Word Error Rate (WER%) for English.

 - FireRedASR-LLM: Designed to achieve state-of-the-art (SOTA) performance and to enable seamless end-to-end speech interaction. It adopts an Encoder-Adapter-LLM framework leveraging large language model (LLM) capabilities.
 - FireRedASR-AED: Designed to balance high performance and computational efficiency and to serve as an effective speech representation module in LLM-based speech models. It utilizes an Attention-based Encoder-Decoder (AED) architecture.
 ## Evaluation
 Results are reported in Character Error Rate (CER%) for Chinese and Word Error Rate (WER%) for English.