You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The docs here mention that TIMIT reports WER, but this dataset typically serves as a benchmark for phone error rate (PER), because it’s one of the few resources that have manually annotated phone segments. I recommend to fix and clarify that in the README:
For example, datasets such as [LibriSpeech](https://huggingface.co/datasets/librispeech_asr) report a WER in the 1.8-3.3 range, whereas ASR models evaluated on [Timit](https://huggingface.co/datasets/timit_asr) report a WER in the 8.3-20.4 range.
I think it would be good to have a clear difference between word/character/phone/token error rate (WER/CER/PER/TER) at the library level.
The text was updated successfully, but these errors were encountered:
The docs here mention that TIMIT reports WER, but this dataset typically serves as a benchmark for phone error rate (PER), because it’s one of the few resources that have manually annotated phone segments. I recommend to fix and clarify that in the README:
evaluate/metrics/wer/README.md
Line 68 in c1141b0
I think it would be good to have a clear difference between word/character/phone/token error rate (WER/CER/PER/TER) at the library level.
The text was updated successfully, but these errors were encountered: