how to set skip_special_tokens and timestamp level?

[MrRace]

How to set parameters similar to skip_special_tokens when generating ASR results? Additionally, does it support ASR results at the timestamp level?

[ggzzzzz628]

same problem

[LauraGPT]

skip_special_tokens：please update funasr-1.1.1 timestamp： on going

[yaohongfenglove]

When is the timestamp level expected to be released? We really need this ability. Thanks

[yaohongfenglove]

How to implement timestamp function? Would you give me some ideas

[gaochangfeng]

How to implement timestamp function? Would you give me some ideas use the forced_align provided by the torchaudio like:

alignment,  scores = torchaudio.functional.forced_align(ctc_probs, preds.unsqueeze(0), None, None, blank=0)

[laubonghaudoi]

alignment, scores = torchaudio.functional.forced_align(ctc_probs, preds.unsqueeze(0), None, None, blank=0) 呢個係點用嘅？

[indiejoseph]

@laubonghaudoi 睇下呢度 https://colab.research.google.com/github/pytorch/audio/blob/gh-pages/main/_downloads/97729a601eea05725da9715649633311/ctc_forced_alignment_api_tutorial.ipynb#scrollTo=AeFF8bo3YLoq

[superme32767]

Is there any solution now, about the timestamp level