Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Spanish
whisper
hf-asr-leaderboard
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("ctam8736/whisper-tiny-es")
model = AutoModelForSpeechSeq2Seq.from_pretrained("ctam8736/whisper-tiny-es")Quick Links
Whisper Small Papi/Es
This model is a fine-tuned version of openai/whisper-tiny on the Papi ASR Test dataset. It achieves the following results on the evaluation set:
- Loss: 0.1243
- Wer: 29.9772
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: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0881 | 0.34 | 200 | 0.1414 | 23.3066 |
| 0.0563 | 0.69 | 400 | 0.1388 | 23.8738 |
| 0.0416 | 1.03 | 600 | 0.1367 | 26.2630 |
| 0.044 | 1.38 | 800 | 0.1295 | 29.1289 |
| 0.0546 | 1.72 | 1000 | 0.1243 | 29.9772 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 5
Model tree for ctam8736/whisper-tiny-es
Base model
openai/whisper-tinyDataset used to train ctam8736/whisper-tiny-es
Evaluation results
- Wer on Papi ASR Testself-reported29.977
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ctam8736/whisper-tiny-es")