Abstractive summarization from Audio Transcription
This work addresses the challenge of making advanced AI models accessible for audio summarization tasks without extensive resources, but it is incremental as it applies known methods to a new domain.
The paper tackles the problem of high computational resource requirements for training large language models by proposing an end-to-end audio summarization model using existing fine-tuning techniques like LoRA and quantization, and evaluates their effectiveness for this specific task.
Currently, large language models are gaining popularity, their achievements are used in many areas, ranging from text translation to generating answers to queries. However, the main problem with these new machine learning algorithms is that training such models requires large computing resources that only large IT companies have. To avoid this problem, a number of methods (LoRA, quantization) have been proposed so that existing models can be effectively fine-tuned for specific tasks. In this paper, we propose an E2E (end to end) audio summarization model using these techniques. In addition, this paper examines the effectiveness of these approaches to the problem under consideration and draws conclusions about the applicability of these methods.