Search Results - "K, Thennal D"

Large Language Models Are Overparameterized Text Encoders by K, Thennal D, Fischer, Tim, Biemann, Chris

“…Large language models (LLMs) demonstrate strong performance as text embedding models when finetuned with supervised contrastive training. However, their large…”
Get full text

Fisher Mask Nodes for Language Model Merging by K, Thennal D, Nathan, Ganesh, S, Suchithra M

“…Fine-tuning pre-trained models provides significant advantages in downstream performance. The ubiquitous nature of pre-trained models such as BERT and its…”
Get full text

Advocating Character Error Rate for Multilingual ASR Evaluation by K, Thennal D, James, Jesin, Gopinath, Deepa P, K, Muhammed Ashraf

“…Automatic speech recognition (ASR) systems have traditionally been evaluated using English datasets, with the word error rate (WER) serving as the predominant…”
Get full text

IMaSC -- ICFOSS Malayalam Speech Corpus by Gopinath, Deepa P, K, Thennal D, Nair, Vrinda V, S, Swaraj K, G, Sachin

“…Modern text-to-speech (TTS) systems use deep learning to synthesize speech increasingly approaching human quality, but they require a database of high quality…”
Get full text