Recent Error
Hey there.
I've been using this model for Hebrew Diarization. It was working fine. Recently I'm getting this error:
2023-10-05 19:59:13.529821: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.0.9.post0. To apply the upgrade to your files permanently, run python -m pytorch_lightning.utilities.upgrade_checkpoint --file ../root/.cache/torch/whisperx-vad-segmentation.bin
Model was trained with pyannote.audio 0.0.1, yours is 3.0.0. Bad things might happen unless you revert pyannote.audio to 0.x.
Performing transcription...
Downloading (…)rocessor_config.json: 100% 158/158 [00:00<00:00, 586kB/s]
Downloading (…)okenizer_config.json: 100% 240/240 [00:00<00:00, 1.04MB/s]
Downloading (…)lve/main/config.json: 100% 1.56k/1.56k [00:00<00:00, 6.70MB/s]
Downloading (…)olve/main/vocab.json: 100% 304/304 [00:00<00:00, 1.88MB/s]
Downloading (…)in/added_tokens.json: 100% 36.0/36.0 [00:00<00:00, 181kB/s]
Downloading (…)cial_tokens_map.json: 100% 85.0/85.0 [00:00<00:00, 625kB/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Downloading model.safetensors: 100% 1.26G/1.26G [00:31<00:00, 39.5MB/s]
Performing alignment...
Traceback (most recent call last):
File "/usr/local/bin/whisperx", line 8, in
sys.exit(cli())
File "/usr/local/lib/python3.10/dist-packages/whisperx/transcribe.py", line 195, in cli
result = align(result["segments"], align_model, align_metadata, input_audio, device, interpolate_method=interpolate_method, return_char_alignments=return_char_alignments, print_progress=print_progress)
File "/usr/local/lib/python3.10/dist-packages/whisperx/alignment.py", line 227, in align
trellis = get_trellis(emission, tokens, blank_id)
File "/usr/local/lib/python3.10/dist-packages/whisperx/alignment.py", line 359, in get_trellis
trellis[t, 1:] + emission[t, blank_id],
IndexError: index 33 is out of bounds for dimension 1 with size 31
Execution time: 93.00095582008362 seconds
But, when I use your other model (imvladikon/wav2vec2-xls-r-300m-lm-hebrew), I don't get the error.
Has there been some change that's causing the error?
Thanks