metadata

language:
  - mt
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_7_0
  - generated_from_trainer
  - mt
  - robust-speech-event
  - model_for_talk
  - hf-asr-leaderboard
datasets:
  - mozilla-foundation/common_voice_7_0
model-index:
  - name: XLS-R-300M - Maltese
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 7
          type: mozilla-foundation/common_voice_7_0
          args: mt
        metrics:
          - name: Test WER
            type: wer
            value: 23.503
          - name: Test CER
            type: cer
            value: 5.065

wav2vec2-large-xls-r-300m-maltese

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - MT dataset. It achieves the following results on the evaluation set:

Loss: 0.2005
Wer: 0.1897

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: 7e-05
train_batch_size: 32
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2000
num_epochs: 100.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.2238	18.02	2000	0.3911	0.4310
0.7871	36.04	4000	0.2063	0.2309
0.6653	54.05	6000	0.1960	0.2091
0.5861	72.07	8000	0.1986	0.2000
0.5283	90.09	10000	0.1993	0.1909

Framework versions

Transformers 4.16.0.dev0
Pytorch 1.10.1+cu102
Datasets 1.17.1.dev0
Tokenizers 0.11.0