(cfg) == 1: # this is hit if config object is nested in directory that is named after model type model_type = next(iter(cfg)) if model_type in MODEL_DATACLASS_REGISTRY: cfg = cfg[model_type] else: raise Exception( "Could not infer model type from directory. Please add _name ...
Then I run " python /data/lby/task/fairseq/examples/speech_recognition/infer.py /data/lby/task/fairseq/examples/wav2vec/fine --task audio_finetuning --nbest 1 --path /data/lby/task/fairseq/outputs/2023-05-23/09-57-25/checkpoints/checkpoint_best.pt --gen-subset $subset --results-path...
PYTHONPATH=/path/fairseq/ python3 examples/speech_recognition/infer.py /path/audio_file/wav2vec/ --task audio_pretraining \ --nbest 1 --path /path/audio_file/wav2vec_small.pt --gen-subset valid --results-path /path/audio_file/wav2vec/tmp/am/ --w2l-decoder kenlm \ --lm-model /...
reference_type=GenerationConfig object_type=GenerationConfig I believe it is interesting to maintain compatibility with old models. Dec 27, 2020 I solved it by manually adjusting the parameter in the saved model from False to 'hard'. You need to do that for all occurrences of the parameter in...
(optional) - `47fd985`: Deprecate old Masked LM components - `5f78106`: Set mmap as default dataset format and infer format automatically - Misc fixes for sampling - Misc fixes to support PyTorch 1.2 Pull Request resolved: https://github.com/pytorch/fairseq/pull/1017 Differential Revision: ...