--- license: cc-by-nc-4.0 base_model: facebook/mms-1b-all tags: - generated_from_trainer datasets: - common_voice_6_1 metrics: - wer model-index: - name: wav2vec2-large-mms-1b-turkish-colab results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: common_voice_6_1 type: common_voice_6_1 config: tr split: test args: tr metrics: - name: Wer type: wer value: 0.9835563272393014 --- # wav2vec2-large-mms-1b-turkish-colab This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_6_1 dataset. It achieves the following results on the evaluation set: - Loss: 2.4395 - Wer: 0.9836 ## 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: 0.001 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:------:| | 6.2025 | 0.46 | 100 | 5.8610 | 1.0478 | | 3.2809 | 0.92 | 200 | 3.5010 | 1.0029 | | 3.0173 | 1.38 | 300 | 3.2271 | 0.9990 | | 2.8897 | 1.83 | 400 | 3.4469 | 0.9981 | | 2.8081 | 2.29 | 500 | 3.1375 | 1.0044 | | 2.7393 | 2.75 | 600 | 2.6899 | 0.9948 | | 2.5172 | 3.21 | 700 | 2.7153 | 0.9949 | | 2.4154 | 3.67 | 800 | 2.4395 | 0.9836 | ### Framework versions - Transformers 4.33.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.4 - Tokenizers 0.13.3