Edit model card

Whisper finetuned for ceb

This model is a fine-tuned version of openai/whisper-small on the Fleurs Ceb subset, LSK nonsynthetic, Onetalk Q&A, and Ceb sentences dataset dataset.

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-06
  • train_batch_size: 4
  • eval_batch_size: 8
  • 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: 100
  • training_steps: 20000

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
11
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 nlewins/whisper-small-translate-X-gen2-examples-quality-step4-1e-6

Finetuned
(1868)
this model

Space using nlewins/whisper-small-translate-X-gen2-examples-quality-step4-1e-6 1