anton-l's picture
anton-l HF staff
Upload README.md
2dbe318
metadata
language:
  - ro
license: apache-2.0
tags:
  - automatic-speech-recognition
  - generated_from_trainer
  - hf-asr-leaderboard
  - model_for_talk
  - mozilla-foundation/common_voice_7_0
  - ro
  - robust-speech-event
datasets:
  - mozilla-foundation/common_voice_7_0
model-index:
  - name: XLS-R-300M - Romanian
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 7
          type: mozilla-foundation/common_voice_7_0
          args: ro
        metrics:
          - name: Test WER
            type: wer
            value: 14.194
          - name: Test CER
            type: cer
            value: 3.288
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Robust Speech Event - Dev Data
          type: speech-recognition-community-v2/dev_data
          args: ro
        metrics:
          - name: Test WER
            type: wer
            value: 40.869
          - name: Test CER
            type: cer
            value: 12.049
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Robust Speech Event - Test Data
          type: speech-recognition-community-v2/eval_data
          args: ro
        metrics:
          - name: Test WER
            type: wer
            value: 47.2

wav2vec2-large-xls-r-300m-romanian

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

  • Loss: 0.1167
  • Wer: 0.1421

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: 50.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
1.1973 8.89 2000 0.4481 0.4849
0.6005 17.78 4000 0.1420 0.1777
0.5248 26.67 6000 0.1303 0.1651
0.4871 35.56 8000 0.1207 0.1523
0.4428 44.44 10000 0.1143 0.1425

Framework versions

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