[sarabande]

I'm trying to use this on a 3M mp3 file to test ASR with language code deu, CPU only, and I keep getting this error -- are there limits to the MMS inference?

  File "fairseq/data/data_utils_fast.pyx", line 30, in fairseq.data.data_utils_fast.batch_by_size_vec
    assert max_tokens <= 0 or np.max(num_tokens_vec) <= max_tokens, (
  AssertionError: Sentences lengths should not exceed max_tokens=4000000
  Traceback (most recent call last):
  File "/home/xxx/fairseq/examples/mms/asr/infer/mms_infer.py", line 52, in <module>
    process(args)
  File "/home/xxx/fairseq/examples/mms/asr/infer/mms_infer.py", line 44, in process

[willn]

Same error here, CPU only, haven't find out a way to run this on GPU (cuda) yet