Hugging Face's logo

Shawal777
/
nyankole_wav2vec2-runpod-unf

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
nyankole_wav2vec2-runpod-unf / README.md
Shawal777's picture
Shawal777
End of training
597d49a verified
preview code
|
raw
history blame contribute delete
2.11 kB
metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - generated_from_trainer
model-index:
  - name: nyankole_wav2vec2-runpod-unf
    results: []

Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases

nyankole_wav2vec2-runpod-unf

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on an unknown dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.6801
  • eval_wer: 0.5843
  • eval_runtime: 36.7511
  • eval_samples_per_second: 5.115
  • eval_steps_per_second: 0.653
  • epoch: 28.9976
  • step: 6104

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: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 100
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.1.0+cu118
  • Datasets 2.20.0
  • Tokenizers 0.19.1