Jzuluaga's picture
updating the repo with the fine-tuned model
e0def8d
# Running on vgnf007
# Started at Wed 30 Nov 07:36:30 CET 2022
# python3 src/eval_model.py --language-model experiments/data/atcosim_uwb_atcc/train/lm/atcosim_uwb_atcc_4g.binary --pretrained-model experiments/results/bs_exp/linear/wav2vec2-large-960h-lv60-self/atcosim_uwb_atcc/0.0ld_0.0ad_0.0attd_0.05fpd_0.075mtp_12mtl_0.0mfp_12mfl_1acc/ --print-output true --test-set experiments/data/atcosim_corpus/train
Integrating a LM by shallow fusion, results should be better
*** Loading the Wav2Vec 2.0 model, loading... ***
Traceback (most recent call last):
File "/remote/idiap.svm/temp.speech01/jzuluaga/experiments/journal/asr/github/w2v2-air-traffic/src/eval_model.py", line 250, in <module>
main()
File "/remote/idiap.svm/temp.speech01/jzuluaga/experiments/journal/asr/github/w2v2-air-traffic/src/eval_model.py", line 152, in main
processor, processor_ctc_kenlm, model = get_kenlm_processor(path_model, path_lm)
File "/remote/idiap.svm/temp.speech01/jzuluaga/experiments/journal/asr/github/w2v2-air-traffic/src/eval_model.py", line 65, in get_kenlm_processor
path_tokenizer + "/vocab.json",
TypeError: unsupported operand type(s) for +: 'PosixPath' and 'str'
# Accounting: time=25 threads=1
# Finished at Wed 30 Nov 07:36:55 CET 2022 with status 1