README.md

metadata

language:
  - sv
license: cc0-1.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_9_0
  - generated_from_trainer
  - sv
datasets:
  - mozilla-foundation/common_voice_9_0
model-index:
  - name: XLS-R-300M - Swedish
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_9_0
          type: mozilla-foundation/common_voice_9_0
          split: test
          args: sv-SE
          WER: null
        metrics:
          - name: Test WER
            type: wer
            value: 7.72
          - name: Test CER
            type: cer
            value: 2.61
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: speech-recognition-community-v2/dev_data
          type: speech-recognition-community-v2/dev_data
          split: validation
          args: sv
        metrics:
          - name: Test WER
            type: wer
            value: 16.23
          - name: Test CER
            type: cer
            value: 8.21
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: speech-recognition-community-v2/dev_data
          type: speech-recognition-community-v2/dev_data
          split: test
          args: sv
        metrics:
          - name: Test WER
            type: wer
            value: 15.08
          - name: Test CER
            type: cer
            value: 7.51

This model is a fine-tuned version of KBLab/wav2vec2-large-voxrex on the MOZILLA-FOUNDATION/COMMON_VOICE_9_0 - SV-SE dataset. It achieves the following results on the evaluation set ("test" split, without LM):

• Loss: 0.1318
• Wer: 0.1121

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: 7.5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 100.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.9099	10.42	1000	2.8369	1.0
1.0745	20.83	2000	0.1957	0.1673
0.934	31.25	3000	0.1579	0.1389
0.8691	41.66	4000	0.1457	0.1290
0.8328	52.08	5000	0.1435	0.1205
0.8068	62.5	6000	0.1350	0.1191
0.7822	72.91	7000	0.1347	0.1155
0.7769	83.33	8000	0.1321	0.1131
0.7678	93.75	9000	0.1321	0.1115

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 2.2.2
• Tokenizers 0.11.0