search

TensorSpeech / TensorFlowASR

:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords
https://huylenguyen.com/asr
Apache License 2.0
941 stars 245 forks source link

best practices for confidence extraction #56

Open danielkope opened 4 years ago

danielkope commented 4 years ago

What would be the best way to show/extract the confidence of the recognition (greedy or beam search) during inference. The sequence/word confidence would be interesting to see.

nglehuy commented 4 years ago

@danielkope What do you mean the confidence of the recognition?

danielkope commented 4 years ago

Confidence scores of the hypothesis

On Wed 25. Nov 2020 at 16:59, Nguyễn Lê Huy notifications@github.com wrote:

@danielkope https://github.com/danielkope What do you mean the confidence of the recognition?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/TensorSpeech/TensorFlowASR/issues/56#issuecomment-733795678, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFLFFISPT7N4IE24QY4RGG3SRUSXLANCNFSM4UCGUFTQ .

nglehuy commented 3 years ago

I haven't seen this evaluation for speech recognition yet. Do you have any documents?