Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("EYEDOL/english-ASR2")
model = AutoModelForSpeechSeq2Seq.from_pretrained("EYEDOL/english-ASR2")Quick Links
English_ASR2
This model is a fine-tuned version of EYEDOL/english-ASR on the misc_naija_english dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
- Wer: 0.8855
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0001 | 8.9286 | 3000 | 0.0001 | 0.8855 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for EYEDOL/english-ASR2
Dataset used to train EYEDOL/english-ASR2
Evaluation results
- Wer on misc_naija_englishself-reported0.886
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="EYEDOL/english-ASR2")