wav2vec2-in-hindi-2

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5608
• Wer: 1.0125

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: 0.0001
• train_batch_size: 32
• 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: 500
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.1593	6.25	200	4.3070	1.0
3.4289	12.5	400	3.3933	1.0
1.3192	18.75	600	0.8550	1.0060
0.4099	25.0	800	0.5886	1.0133
0.2479	31.25	1000	0.6010	1.0141
0.1942	37.5	1200	0.5653	1.0120
0.1599	43.75	1400	0.5682	1.0144
0.1413	50.0	1600	0.5608	1.0125

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3