Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("mscs23021/Whisper_Small_Final")
model = AutoModelForSpeechSeq2Seq.from_pretrained("mscs23021/Whisper_Small_Final", device_map="auto")Quick Links
Whisper_Small_Final
This model is a fine-tuned version of mscs23021/Whisper_small_urdu_t on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5675
- Wer: 110.7983
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 13
Model tree for mscs23021/Whisper_Small_Final
Base model
mscs23021/Whisper_small_urdu_tEvaluation results
- Wer on common_voice_13_0test set self-reported110.798
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mscs23021/Whisper_Small_Final")