Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("spraveenkumar1318/whisper-tiny_en-fine-tuned")
model = AutoModelForSpeechSeq2Seq.from_pretrained("spraveenkumar1318/whisper-tiny_en-fine-tuned")Quick Links
Whisper Tiny Fine Tuned
This model is a fine-tuned version of openai/whisper-tiny.en on the custom dataset. It achieves the following results on the evaluation set:
- Loss: 0.5021
- Wer: 196.4646
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: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.2121 | 50.0 | 500 | 0.5021 | 196.4646 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for spraveenkumar1318/whisper-tiny_en-fine-tuned
Base model
openai/whisper-tiny.en
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="spraveenkumar1318/whisper-tiny_en-fine-tuned")