anton-l/wav2vec2-xls-r-common_voice-tr-ft-stream

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

wav2vec2-xls-r-common_voice-tr-ft-stream

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the COMMON_VOICE - TR dataset. It achieves the following results on the evaluation set:

• —Loss: 0.3519
• —Wer: 0.2927
• —Cer: 0.0694

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
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 64
• —totalevalbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —training_steps: 5000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.16.0.dev0
• —Pytorch 1.10.2
• —Datasets 1.18.2
• —Tokenizers 0.10.3