Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
English
whisper
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("NemesisAlm/whisper-tiny-en")
model = AutoModelForSpeechSeq2Seq.from_pretrained("NemesisAlm/whisper-tiny-en")Quick Links
Whisper Tiny en - NemesisAlm
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI minds14 en-US dataset. It achieves the following results on the evaluation set:
- Loss: 0.5820
- Wer Ortho: 0.3567
- Wer: 0.3482
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: 5
- training_steps: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.6196 | 1.79 | 50 | 0.5820 | 0.3567 | 0.3482 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 8
Dataset used to train NemesisAlm/whisper-tiny-en
Evaluation results
- Wer on PolyAI minds14 en-USself-reported0.348
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NemesisAlm/whisper-tiny-en")