Update README.md
Browse files
README.md
CHANGED
|
@@ -69,7 +69,7 @@ against three well-known AudioLLMs: `Qwen2-Audio 7B`, `WavLLM`, and `SALMONN`. W
|
|
| 69 |
which feeds the transcriptions recognized by Whisper-large-v2 and the instruction prompts to a Gemma2 9B CPT SEA-LIONv3 Instruct model to
|
| 70 |
get the responses. We tuned its hyperparameters and prompt template to optimise performance across
|
| 71 |
various speech-to-text tasks. As is shown in the following table, MERaLiON-AudioLLM performs better in the Singapore local context,
|
| 72 |
-
as evidenced by evaluation results on Singapore's [Multitask National Speech Corpus](MERaLiON/
|
| 73 |
|
| 74 |
> [!NOTE]
|
| 75 |
> MNSC is a multitask speech understanding dataset derived and further annotated from [IMDA NSC Corpus](https://www.imda.gov.sg/how-we-can-help/national-speech-corpus).
|
|
|
|
| 69 |
which feeds the transcriptions recognized by Whisper-large-v2 and the instruction prompts to a Gemma2 9B CPT SEA-LIONv3 Instruct model to
|
| 70 |
get the responses. We tuned its hyperparameters and prompt template to optimise performance across
|
| 71 |
various speech-to-text tasks. As is shown in the following table, MERaLiON-AudioLLM performs better in the Singapore local context,
|
| 72 |
+
as evidenced by evaluation results on Singapore's [Multitask National Speech Corpus](https://huggingface.co/datasets/MERaLiON/Multitask-National-Speech-Corpus-v1) (MNSC) datasets.
|
| 73 |
|
| 74 |
> [!NOTE]
|
| 75 |
> MNSC is a multitask speech understanding dataset derived and further annotated from [IMDA NSC Corpus](https://www.imda.gov.sg/how-we-can-help/national-speech-corpus).
|