Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Marathi
whisper
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("simran14/saved_med_model1")
model = AutoModelForSpeechSeq2Seq.from_pretrained("simran14/saved_med_model1")Quick Links
simrank14 Whisper medium 1
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2588
- Wer: 14.4732
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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.017 | 3.5587 | 1000 | 0.2588 | 14.4732 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.1.dev0
- Tokenizers 0.19.1
- Downloads last month
- 3
Model tree for simran14/saved_med_model1
Base model
openai/whisper-mediumEvaluation results
- Wer on Common Voice 11.0test set self-reported14.473
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="simran14/saved_med_model1")