metadata

language:
  - mr
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_8_0
  - generated_from_trainer
  - mr
  - robust-speech-event
  - model_for_talk
  - hf-asr-leaderboard
datasets:
  - mozilla-foundation/common_voice_8_0
model-index:
  - name: XLS-R-300M - Marathi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 8
          type: mozilla-foundation/common_voice_8_0
          args: mr
        metrics:
          - name: Test WER
            type: wer
            value: 55.716
          - name: Test CER
            type: cer
            value: 13.842

wav2vec2-large-xls-r-300m-marathi-cv8

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - MR dataset. It achieves the following results on the evaluation set:

Loss: 0.6483
Wer: 0.6049

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: 32
eval_batch_size: 16
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: 100.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.671	22.73	500	1.3618	0.9499
1.1599	45.45	1000	0.6330	0.6627
0.8252	68.18	1500	0.6226	0.6426
0.6424	90.91	2000	0.6359	0.6041

Framework versions

Transformers 4.17.0.dev0
Pytorch 1.10.2+cu102
Datasets 1.18.3
Tokenizers 0.11.0