Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Romanian
whisper
hf-asr-leaderboard
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("iulik-pisik/busu_model_tiny")
model = AutoModelForSpeechSeq2Seq.from_pretrained("iulik-pisik/busu_model_tiny")Quick Links
Whisper Tiny Romanian - Vreme Florin Busuioc
This model is a fine-tuned version of openai/whisper-tiny on the Vreme ProTv - Florin Busuioc dataset. It achieves the following results on the evaluation set:
- Loss: 0.3196
- Wer: 15.5509
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: 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0349 | 7.63 | 1000 | 0.2170 | 16.5147 |
| 0.0018 | 15.27 | 2000 | 0.2874 | 15.6030 |
| 0.0009 | 22.9 | 3000 | 0.3114 | 15.5249 |
| 0.0006 | 30.53 | 4000 | 0.3196 | 15.5509 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for iulik-pisik/busu_model_tiny
Base model
openai/whisper-tinyDataset used to train iulik-pisik/busu_model_tiny
Evaluation results
- Wer on Vreme ProTv - Florin Busuiocself-reported15.551
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="iulik-pisik/busu_model_tiny")