Hugging Face's logo

junnei
/
Phi-4-multimodal-instruct-ko-speech

Automatic Speech Recognition
Transformers
Safetensors
Korean
phi4mm
text-generation
custom_code
Eval Results
Model card Files Community
junnei commited on
Commit
4102dd3
·
verified ·
1 Parent(s): 2e1b1c7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -69,12 +69,12 @@ Script is retrieved from [here](https://gist.github.com/seastar105/d1d8983b27611
69
 
70
  Compared to [Phi-4-mm-inst-zeroth-kor](https://huggingface.co/seastar105/Phi-4-mm-inst-zeroth-kor) and [Phi-4-multimodal-finetune-ko-speech](https://huggingface.co/daekeun-ml/Phi-4-multimodal-finetune-ko-speech), ASR is significantly improved.
71
 
72
- | Model | zeroth-CER | zeroth-WER | fleurs-ko2en | fleurs-ko2en-cot | fleurs-en2ko | fleurs-en2ko-cot |
73
- |------------------------------------------------|-------------|------------|--------------|------------------|--------------|------------------|
74
- | original | 198.32 | - | 5.63 | 2.42 | 6.86 | 4.17 |
75
- | daekeun-ml/Phi-4-multimodal-finetune-ko-speech | 1.61 | 3.54 | 7.67 | 8.38 | 12.31 | 9.69 |
76
- | seastar105/Phi-4-mm-inst-zeroth-kor | 7.02 | - | 7.07 | 9.19 | 13.08 | 9.35 |
77
- | [**ASR finetune**][ASR] | **1.31** | 2.95 | 7.46 | 6.24 | 12.15 | 8.91 |
78
- | + 1 epoch finetune with [Covost-Ko][Covost2-ko]| 3.88 | - | **8.07** | **10.09** | **18.82** | **15.41** |
79
- | **AST finetuned model(this model)** | **1.77** | **2.99** | **8.01** | **9.09** | **17.09** | **11.82** |
80
 
 
69
 
70
  Compared to [Phi-4-mm-inst-zeroth-kor](https://huggingface.co/seastar105/Phi-4-mm-inst-zeroth-kor) and [Phi-4-multimodal-finetune-ko-speech](https://huggingface.co/daekeun-ml/Phi-4-multimodal-finetune-ko-speech), ASR is significantly improved.
71
 
72
+ | Model | zeroth-CER | zeroth-WER | fleurs-ko_en-BLEU | fleurs-ko_en-cot-BLEU | fleurs-en_ko-BLEU | fleurs-en_ko-cot-BLEU |
73
+ |------------------------------------------------|-------------|------------|-------------------|-----------------------|-------------------|-----------------------|
74
+ | original | 198.32 | - | 5.63 | 2.42 | 6.86 | 4.17 |
75
+ | daekeun-ml/Phi-4-multimodal-finetune-ko-speech | 1.61 | 3.54 | 7.67 | 8.38 | 12.31 | 9.69 |
76
+ | seastar105/Phi-4-mm-inst-zeroth-kor | 7.02 | - | 7.07 | 9.19 | 13.08 | 9.35 |
77
+ | [**ASR finetune**][ASR] | **1.31** | 2.95 | 7.46 | 6.24 | 12.15 | 8.91 |
78
+ | + 1 epoch finetune with [Covost-Ko][Covost2-ko]| 3.88 | - | **8.07** | **10.09** | **18.82** | **15.41** |
79
+ | **AST finetuned model(this model)** | **1.77** | **2.99** | **8.01** | **9.09** | **17.09** | **11.82** |
80