shivam/wav2vec2-xls-r-hindi

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMONVOICE7_0 - HI dataset. It achieves the following results on the evaluation set:

• —Loss: 1.2282
• —Wer: 0.6838

Evaluation results on Common Voice 7 "test" (Running ./eval.py):

With LM

• —WER: 52.30
• —CER: 26.09

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: 7.5e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 2000
• —num_epochs: 50.0
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.16.0.dev0
• —Pytorch 1.10.1+cu113
• —Datasets 1.18.1.dev0
• —Tokenizers 0.11.0