No weights were modified — this is a format conversion only.
1eole predict \
2 -config eval_config.yaml \
3 -model_path whisper-large-v2-eole \
4 -src audio_files.txt \
5 -output transcriptions.txt \
6 -language en \
7 -task transcribe \
8 -gpu_ranks 0
All evaluations use beam size 5.
1@misc{radford2023robust,
2 title={Robust Speech Recognition via Large-Scale Weak Supervision},
3 author={Alec Radford and Jong Wook Kim and Tao Xu and Greg Brockman and Christine McLeavey and Ilya Sutskever},
4 year={2023},
5 eprint={2212.04356},
6 archivePrefix={arXiv},
7 primaryClass={eess.AS}
8}
