Abdullah010/wav2vec2-urdu-asr-commom-voice-9.0_model_final
018
<!-- 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-urdu-asr-commom-voice-9.0modelfinal
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 2.9620
- Wer: 1.0059
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: 0.0001
- trainbatchsize: 16
- evalbatchsize: 8
- seed: 42
- gradientaccumulationsteps: 2
- totaltrainbatch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: linear
- lrschedulerwarmup_steps: 1000
- num_epochs: 5
Training results
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1