Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("bgstud/whisper-small-libirClean-vs-commonNative-en")
model = AutoModelForSpeechSeq2Seq.from_pretrained("bgstud/whisper-small-libirClean-vs-commonNative-en")Quick Links
whisper-small-libirClean-vs-commonNative-en
This model is a fine-tuned version of openai/whisper-small on the librispeech_asr dataset. It achieves the following results on the evaluation set:
- Loss: 2.3358
- Wer: 85.5379
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: 10
- training_steps: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.2481 | 0.08 | 10 | 3.5688 | 21.1895 |
| 0.7793 | 0.16 | 20 | 2.8307 | 38.9990 |
| 0.5443 | 0.24 | 30 | 2.4196 | 67.0458 |
| 0.4484 | 0.32 | 40 | 2.2903 | 71.1732 |
| 0.4086 | 0.4 | 50 | 2.3358 | 85.5379 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 7
Dataset used to train bgstud/whisper-small-libirClean-vs-commonNative-en
Evaluation results
- Wer on librispeech_asrself-reported85.538
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bgstud/whisper-small-libirClean-vs-commonNative-en")