Whisper Small Quechua - ZLTech

This model is a fine-tuned version of openai/whisper-small on the Genesis Cuzco Quechua Bible dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0000

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
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.0001 363.6364 500 0.0001
0.0 727.2727 1000 0.0000
0.0 1090.9091 1500 0.0000
0.0 1454.5455 2000 0.0000
0.0 1818.1818 2500 0.0000
0.0 2181.8182 3000 0.0000
0.0 2545.4545 3500 0.0000
0.0 2909.0909 4000 0.0000
0.0 3272.7273 4500 0.0000
0.0 3636.3636 5000 0.0000

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.19.1
Downloads last month
23
Safetensors
Model size
242M params
Tensor type
F32
ยท
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for pollitoconpapass/whisper-small-finetuned

Finetuned
(2103)
this model

Dataset used to train pollitoconpapass/whisper-small-finetuned

Space using pollitoconpapass/whisper-small-finetuned 1