This model repository is copied from
daniel_whisper_finetune_large_v3_turbo_v2 and is a fully functional subset of it.
The purpose of copying this converted model is to use it directly in projects without much code modifications and without needing to download the entire repository that includes safetensors and ggml models. The original creator, Daniel, did not create a separate repository for the ct2 model but placed it in a subdirectory of the source model. Thanks to Daniel for creating this fine-tuned model.
This model is a fine-tuned version of
openai/whisper-large-v3-turbo on an unknown dataset.
It achieves the following results on the evaluation set:
This is a personal fine-tune of the Whisper large-v3-turbo model, trained on approximately 1 hour of audio featuring Daniel Rosehill's voice. The training data includes domain-specific vocabulary focused on:
This model was created as a proof of concept for fine-tuning Whisper models for personal use and improved transcription accuracy on domain-specific content.
Fine-tuning was performed using Modal GPU inference infrastructure.
