# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="Serialtechlab/whisper-small-dhivehi-v2")# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("Serialtechlab/whisper-small-dhivehi-v2")
model = AutoModelForSpeechSeq2Seq.from_pretrained("Serialtechlab/whisper-small-dhivehi-v2")Quick Links
whisper-small-dhivehi-v2
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1393
- Wer: 1.2255
- Cer: 1.0799
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.1603 | 1.6556 | 500 | 0.1393 | 3.7878 | 2.4033 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- -
Model tree for Serialtechlab/whisper-small-dhivehi-v2
Base model
openai/whisper-small
# Gated model: Login with a HF token with gated access permission hf auth login