Jun 7, 2024 · This paper proposes LoRA-Whisper, which incorporates LoRA matrix into Whisper for multilingual ASR, effectively mitigating language interference ...
Sep 5, 2024 · Towards this end, we introduce LoRA-Whisper, a parameter-efficient and extensible model for multilingual ASR. LoRA [35], originally ...
Jun 7, 2024 · This paper proposes LoRA-Whisper, which incorporates LoRA matrix into Whisper for multilingual ASR, effectively mitigating language interference.
Sep 4, 2024 · ASR. Conference Paper. LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR. September 2024. DOI:10.21437/Interspeech.2024-892.
Jun 11, 2024 · The LoRA-Whisper paper presents a novel technique for fine-tuning multilingual speech recognition models in a parameter-efficient and extensible manner.
People also ask
What is the difference between TTS and ASR?
How phonotactics affect multilingual and zero shot ASR performance?
Our proposed approach, LoRA-Whisper, effectively eliminates interference between languages by incorporating language-specific LoRA matrices.
LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR ... Recent years have witnessed significant progress in multilingual automatic speech ...
Aug 20, 2024 · LoRA is a parameter-efficient fine-tuning method that only updates a small number of the model's parameters when adapting it to a new task or ...
LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR, Zheshu ... A Parameter-efficient Language Extension Framework for Multilingual ASR ...
LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR · Survey on Controlable Image Synthesis with Deep Learning · MetricNet: Towards Improved ...