Timestamps Issue when transcribing longer audio
#2
by
walshak
- opened
You are trying to return timestamps, but the generation config is not properly set. Make sure to initialize the generation config with the correct attributes that are needed such as no_timestamps_token_id. For more details on how to generate the approtiate config, refer to https://github.com/huggingface/transformers/issues/21878#issuecomment-1451902363
What config will one need to change to avoid this error? especially if one inteds to use the inference Endpoints