Audio
Collection
6 items • Updated
Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("vadhri/whisper-tiny")
model = AutoModelForSpeechSeq2Seq.from_pretrained("vadhri/whisper-tiny")Quick Links
whisper-tiny
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6785
- Wer Ortho: 0.3644
- Wer: 0.3570
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0006 | 17.86 | 500 | 0.6785 | 0.3644 | 0.3570 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 3
Model tree for vadhri/whisper-tiny
Base model
openai/whisper-tinyDataset used to train vadhri/whisper-tiny
Collection including vadhri/whisper-tiny
Evaluation results
- Wer on PolyAI/minds14self-reported0.357
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="vadhri/whisper-tiny")