metadata

library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: wav2vec2-large-xlsr-hindi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: hi
          split: test
          args: hi
        metrics:
          - name: Wer
            type: wer
            value: 0.6569451876767831

wav2vec2-large-xlsr-hindi

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.9008
Wer: 0.6569

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: 0.0003
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 300
num_epochs: 7
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
7.774	1.3605	200	3.5057	1.0
2.6507	2.7211	400	1.2937	0.8401
0.7129	4.0816	600	0.9775	0.7138
0.4318	5.4422	800	0.9152	0.6752
0.3234	6.8027	1000	0.9008	0.6569

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1