# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("Professor/whisper-small-enyo")
model = AutoModelForSpeechSeq2Seq.from_pretrained("Professor/whisper-small-enyo")Quick Links
Whisper Small - Code-Switched (En-Yo)
This model is a fine-tuned version of openai/whisper-small on the codeswitched21hrs 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-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu121
- Datasets 3.4.0
- Tokenizers 0.21.0
- Downloads last month
- 5
Model tree for Professor/whisper-small-enyo
Base model
openai/whisper-small
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Professor/whisper-small-enyo")