Hugging Face's logo

cladsu
/
prueba-large-whisper

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
prueba-large-whisper / README.md
cladsu's picture
cladsu
Model save
1715e20 verified
preview code
|
raw
history blame contribute delete
No virus
1.53 kB
metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: prueba-large-whisper
    results: []

prueba-large-whisper

This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.0424
  • Wer: 75.8721

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: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1
  • training_steps: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.9835 0.0001 5 4.8632 67.3129
3.718 0.0003 10 3.0424 75.8721

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1