README.md

metadata

language:
  - de
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_10_0
  - generated_from_trainer
model-index:
  - name: wav2vec2-xls-r-300m-german
    results: []

wav2vec2-xls-r-300m-german

This model is a fine-tuned version of wav2vec2-xls-r-300m-german on the MOZILLA-FOUNDATION/COMMON_VOICE_10_0 - DE dataset. It achieves the following results on the evaluation set:

• Loss: 0.4842
• Wer: 0.3940

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: 3e-07
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2759	1.0	3612	0.4813	0.3922
0.2672	2.0	7224	0.4796	0.3925

Framework versions

• Transformers 4.21.3
• Pytorch 1.12.1
• Datasets 2.4.0
• Tokenizers 0.12.1