wav2vec2-100m-mls-german-ft

This model is a fine-tuned version of facebook/wav2vec2-xls-r-100m on the MULTILINGUAL_LIBRISPEECH - GERMAN dataset. It achieves the following results on the evaluation set:

• Loss: 2.9325
• Wer: 1.0

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 100.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
8.2135	14.29	500	8.4258	1.0
3.0031	28.57	1000	2.9839	1.0
2.9661	42.86	1500	2.9402	1.0
2.9584	57.14	2000	2.9354	1.0
2.936	71.43	2500	2.9341	1.0
2.9344	85.71	3000	2.9323	1.0
2.9674	100.0	3500	2.9325	1.0

Framework versions

• Transformers 4.13.0.dev0
• Pytorch 1.9.0+cu111
• Datasets 1.15.2.dev0
• Tokenizers 0.10.3