I started looking a bit into Confidence Scores / Self-Training for Speech Recognition for models like Wav2Vec2. The most reasonable way of doing so is to do it on a per-word level basis. With the new output_word_offsets=True it’s quite easy to retrieve the logits scores of the predicted words. E.g…

Confidence Scores / Self-Training for Wav2Vec2 / CTC models

patrickvonplaten April 21, 2022, 11:14am 2

Topic		Replies	Views
Confidence Scores / Self-Training for Wav2Vec2 / CTC models With LM (PyCTCDecode) Research	1	2754	April 21, 2022
Confidence Score For Wav2Vec? 🤗Transformers	0	231	August 8, 2022
Wav2Vec2ForCTC abandons one logit sometimes Models	1	412	October 26, 2022
Pretrained wav2vec2 speech to text - decoded text is gibberish Models	0	358	June 12, 2023
Wav2Vec2: loss growing in training and validation after few epochs Models	6	1864	September 25, 2024