Audio file is not transcribed after 30 second mark.

#16
by kirankumaram - opened

Audio is transcribed or translated only till the 30 second mark for a 3-minute input file. Followed the same procedure as mentioned in the model card. Kindly help

Issue is solved if we use pipeline mentioned in https://huggingface.co/openai/whisper-large-v2/discussions/7#6398809b11095028d87b16a2.

But if we use the pipeline mentioned in model-card, transcription is not taking place after 30 second mark

Sign up or log in to comment