metadata

language:
  - tr
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_16_0
  - generated_from_trainer
datasets:
  - common_voice_16_0
metrics:
  - wer
model-index:
  - name: wav2vec2-common_voice-tr-demo-mini
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - TR
          type: common_voice_16_0
          config: tr
          split: test[0:250]
          args: 'Config: tr, Training split: train[0:3000], Eval split: test[0:250]'
        metrics:
          - name: Wer
            type: wer
            value: 0.9382716049382716

wav2vec2-common_voice-tr-demo-mini

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - TR dataset. It achieves the following results on the evaluation set:

Loss: 0.9823
Wer: 0.9383

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.5333	100	4.0238	1.0
No log	1.0667	200	3.2451	1.0
No log	1.6	300	2.9997	1.0
No log	2.1333	400	1.4256	1.0054
4.5926	2.6667	500	1.2465	0.9730

Framework versions

Transformers 4.42.0.dev0
Pytorch 2.3.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1