Robust Speech Recognition via Large-Scale Weak Supervision
Radford et al., 2023, Robust Speech Recognition via Large-Scale Weak Supervision (Proceedings of the 40th International Conference on Machine Learning (ICML 2023), PMLR 202)
Subscriber deck — free during early access
1 cards in “3.5 Translation” · whole deck
3.5 Translation
- How did Whisper do on X→English speech translation?It set a zero-shot state of the art of 29.1 BLEU on CoVoST2, helped by 68,000 hours of noisy translation data for those languages (vs 861 hours of CoVoST2 training data), with the biggest gains on low-resource languages but no gain on high-resource ones.
- Radford et al., 2023, Robust Speech Recognition via Large-Scale Weak Supervision (Proceedings of the 40th International Conference on Machine Learning (ICML 2023), PMLR 202), §3.5
Source
- Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey and Ilya Sutskever. 2023. Robust Speech Recognition via Large-Scale Weak Supervision. In Proceedings of the 40th International Conference on Machine Learning (ICML 2023), PMLR 202, pp. 28492–28518. https://proceedings.mlr.press/v202/radford23a.html