Multimodal Translation on Nepali Spoken Words (Efficiency Metrics)
12.3Params (M)CNN-LSTM*
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| CNN-LSTM*2026.05 | 12.3 | 1.849 | 35 | 35 | |
| NEST-V12026.05 | 22.1 | 2.189 | 45 | 95 | |
| ASR+Emotion2026.05 | 35.2 | 7.814 | 178 | 178 | |
| ViT-Base2026.05 | 86.6 | 17.534 | 612 | 125 |