# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("marczenko/timit-ft")
model = AutoModelForSpeechSeq2Seq.from_pretrained("marczenko/timit-ft")Quick Links
timit-ft
This model is a fine-tuned version of openai/whisper-small on the timit_asr dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.7722
- eval_wer: 7.1566
- eval_runtime: 335.4678
- eval_samples_per_second: 5.008
- eval_steps_per_second: 0.158
- step: 0
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-06
- train_batch_size: 64
- eval_batch_size: 32
- 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: 5000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.39.3
- Pytorch 2.0.1+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3
Model tree for marczenko/timit-ft
Base model
openai/whisper-small
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="marczenko/timit-ft")