metadata
license: apache-2.0
tags:
- automatic-speech-recognition
- multilingual_librispeech
- generated_from_trainer
datasets:
- multilingual_librispeech
model-index:
- name: wav2vec2-300m-mls-german-ft
results: []
wav2vec2-300m-mls-german-ft
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MULTILINGUAL_LIBRISPEECH - GERMAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.3893
- Wer: 0.2695
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: 0.0005
- train_batch_size: 32
- 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: 500
- num_epochs: 15.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.265 | 7.25 | 500 | 0.4818 | 0.4440 |
| 0.0522 | 14.49 | 1000 | 0.3902 | 0.2725 |
Framework versions
- Transformers 4.13.0.dev0
- Pytorch 1.10.0
- Datasets 1.15.2.dev0
- Tokenizers 0.10.3