wav2vec2-large-mms-1b-korean-colab

This model is a fine-tuned version of facebook/mms-1b-l1107 on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 7.8135
• Wer: 0.9930

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
10.9747	2.63	100	7.8812	0.9990
5.9431	5.26	200	8.2212	0.9960
5.7372	7.89	300	8.1054	0.9930
5.2582	10.53	400	8.2347	0.9940
3.8725	13.16	500	7.7536	0.9940
3.4454	15.79	600	7.7220	0.9930
2.5989	18.42	700	7.8135	0.9930

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3