# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM
processor = AutoProcessor.from_pretrained("sitwala/whisper-large-v3-turbo-anv-zul-150h")
model = AutoModelForMultimodalLM.from_pretrained("sitwala/whisper-large-v3-turbo-anv-zul-150h")Quick Links
Whisper whisper-large-v3-turbo zul
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the dsfsi-anv/za-african-next-voices dataset. It achieves the following results on the evaluation set:
- Loss: 0.3443
- Wer: 25.2022
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.01
- training_steps: 443
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3397 | 1.0 | 443 | 0.3443 | 25.2022 |
Framework versions
- Transformers 4.52.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.4
- Downloads last month
- 2
Model tree for sitwala/whisper-large-v3-turbo-anv-zul-150h
Base model
openai/whisper-large-v3 Finetuned
openai/whisper-large-v3-turbo
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="sitwala/whisper-large-v3-turbo-anv-zul-150h")