Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("mangoo111/eval")
model = AutoModelForSpeechSeq2Seq.from_pretrained("mangoo111/eval")Quick Links
test_whisper
This model is a fine-tuned version of openai/whisper-base on the mangoo111/eval dataset. It achieves the following results on the evaluation set:
- Loss: 0.0539
- Cer: 2.2521
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: Use 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0266 | 2.8818 | 1000 | 0.0650 | 2.6964 |
| 0.0019 | 5.7637 | 2000 | 0.0551 | 2.1164 |
| 0.0011 | 8.6455 | 3000 | 0.0539 | 2.2336 |
| 0.0008 | 11.5274 | 4000 | 0.0539 | 2.2521 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
- Datasets 2.17.1
- Tokenizers 0.21.0
- Downloads last month
- 1
Model tree for mangoo111/eval
Base model
openai/whisper-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mangoo111/eval")