This PR removes Remove the usage of transformers.pipeline from BatchedInferencePipeline because there's no need to use it in the first place
this simplifies the code and removes a requirement
it also fixes #919
it was caused by wrong num_frames argument when finding the alignments, it was assumed that inferring it from encoder output size was sufficient but turned out to cause issues such as #919 when the actual segment size is much less that the inferred size
This PR removes Remove the usage of
transformers.pipeline
fromBatchedInferencePipeline
because there's no need to use it in the first place this simplifies the code and removes a requirement it also fixes #919 it was caused by wrongnum_frames
argument when finding the alignments, it was assumed that inferring it from encoder output size was sufficient but turned out to cause issues such as #919 when the actual segment size is much less that the inferred size