metadata

language:
  - hi
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_7_0
  - generated_from_trainer
  - hi
datasets:
  - wav2vec2-large-xls-r-300m-hi
model-index:
  - name: wav2vec2-large-xls-r-300m-hi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 7
          type: mozilla-foundation/common_voice_7_0
          args: hi
        metrics:
          - name: Test WER
            type: wer
            value: 35.31946325249292
          - name: Test CER
            type: cer
            value: 11.310803379493075

wav2vec2-large-xls-r-300m-hi-CV7

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

Loss: 0.6588
Wer: 0.2987

Training hyperparameters

The following hyperparameters were used during training:

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: 2000
num_epochs: 60
mixed_precision_training: Native AMP

Framework versions

Transformers 4.16.2
Pytorch 1.10.0+cu111
Datasets 1.18.3
Tokenizers 0.11.0