3 contributors

History: 48 commits

marinone94

add first eval on real world dev data

412339d almost 3 years ago

.ipynb_checkpoints
sync almost 3 years ago
language_model
Upload 5-gram lm-boosted decoder almost 3 years ago
.gitattributes

1.18 kB

Upload 5-gram lm-boosted decoder almost 3 years ago
.gitignore

39 Bytes

remove checkpoints from repo almost 3 years ago
README.md

3.6 kB

update model card README.md almost 3 years ago
added_tokens.json

23 Bytes

Training in progress, step 5 almost 3 years ago
all_results.json

402 Bytes

End of training almost 3 years ago
alphabet.json

253 Bytes

Upload 5-gram lm-boosted decoder almost 3 years ago
config.json

2.04 kB

Training in progress, step 500 almost 3 years ago
eval.py

4.42 kB

Add LM in training script almost 3 years ago
eval_results.json

226 Bytes

End of training almost 3 years ago
log_mozilla-foundation_common_voice_7_0_sv-SE_test_predictions.txt

208 kB

cv sv test almost 3 years ago
log_mozilla-foundation_common_voice_7_0_sv-SE_test_targets.txt

210 kB

cv sv test almost 3 years ago
log_speech-recognition-community-v2_dev_data_sv_validation_predictions.txt

12.5 kB

add first eval on real world dev data almost 3 years ago
log_speech-recognition-community-v2_dev_data_sv_validation_targets.txt

12.6 kB

add first eval on real world dev data almost 3 years ago
mozilla-foundation_common_voice_7_0_sv-SE_test_eval_results.txt

47 Bytes

cv sv test almost 3 years ago
prepare_dataset_lm.py

285 Bytes

add eval almost 3 years ago
preprocessor_config.json

260 Bytes

Update processor config with Wav2Vec2ProcessorWithLM as processor_class almost 3 years ago
pytorch_model.bin

1.26 GB
LFS

Training in progress, step 500 almost 3 years ago
requirements.txt

74 Bytes

Add LM in training script almost 3 years ago
run.sh

1.06 kB

Add LM in training script almost 3 years ago
run_speech_recognition_ctc.py

30.7 kB

remove add lm from script almost 3 years ago
special_tokens_map.json

888 Bytes

Upload 5-gram lm-boosted decoder almost 3 years ago
speech-recognition-community-v2_dev_data_sv_validation_eval_results.txt

48 Bytes

add first eval on real world dev data almost 3 years ago
tokenizer_config.json

289 Bytes

Upload 5-gram lm-boosted decoder almost 3 years ago
train_n_gram_lm_with_KenLM.ipynb

84.5 kB

Add LM in training script almost 3 years ago
train_results.json

197 Bytes

End of training almost 3 years ago
trainer_state.json

29.7 kB

End of training almost 3 years ago
training_args.bin

2.99 kB
LFS

Training in progress, step 500 almost 3 years ago
vocab.json

319 Bytes

Training in progress, step 5 almost 3 years ago