Hugging Face's logo

infinitejoy
/
wav2vec2-large-xls-r-300m-odia-cv8

Automatic Speech Recognition
Transformers
PyTorch
Oriya
wav2vec2
mozilla-foundation/common_voice_8_0
Generated from Trainer
Inference Endpoints
Model card Files Community
wav2vec2-large-xls-r-300m-odia-cv8 / README.md
infinitejoy's picture
infinitejoy
update model card README.md
a7074fd
preview code
|
raw
history blame
1.76 kB
metadata
language:
  - or
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_8_0
  - generated_from_trainer
datasets:
  - common_voice
model-index:
  - name: wav2vec2-large-xls-r-300m-odia-cv8
    results: []

wav2vec2-large-xls-r-300m-odia-cv8

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - OR dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8176
  • Wer: 0.5818

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: 0.0003
  • train_batch_size: 32
  • eval_batch_size: 16
  • 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: 100.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.3957 20.83 500 1.0925 0.8111
1.0351 41.67 1000 0.7837 0.6574
0.7396 62.5 1500 0.7674 0.6083
0.5385 83.33 2000 0.8015 0.5812

Framework versions

  • Transformers 4.17.0.dev0
  • Pytorch 1.10.2+cu102
  • Datasets 1.18.3
  • Tokenizers 0.11.0