Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
my_awesome_asr_mind_model – AI Model by HuggingFaceSun | AlphaNeural AI
You can deploy this model and start earning money today!
HuggingFaceSun
/
my_awesome_asr_mind_model
like
0
transformers
pytorch
tensorboard
wav2vec2
automatic-speech-recognition
generated_from_trainer
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
my_awesome_asr_mind_model
This model is a fine-tuned version of
facebook/wav2vec2-base
on the None dataset. It achieves the following results on the evaluation set:
Loss: 3.2641
Wer: 1.0
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: 0.001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 30
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
51.824
1.0
5
42.3534
1.0
48.753
2.0
10
42.3534
1.0
32.07
3.0
15
3.8432
1.0
3.7454
4.0
20
3.2294
1.0
3.2491
5.0
25
3.2486
1.0
3.1421
6.0
30
3.2641
1.0
Framework versions
Transformers 4.28.0
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.13.3
