Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
wav2vec2-2-rnd-2-layer – AI Model by sanchit-gandhi | AlphaNeural AI
You can deploy this model and start earning money today!
sanchit-gandhi
/
wav2vec2-2-rnd-2-layer
like
0
transformers
pytorch
tensorboard
speech-encoder-decoder
automatic-speech-recognition
generated_from_trainer
librispeech_asr
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
This model was trained from scratch on the librispeech_asr dataset. It achieves the following results on the evaluation set:
Loss: 5.2188
Wer: 0.9238
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: 3e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
num_epochs: 20.0
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
5.7093
6.73
1500
5.7514
1.2104
5.642
13.45
3000
5.2188
0.9238
Framework versions
Transformers 4.17.0.dev0
Pytorch 1.10.2+cu113
Datasets 1.18.3
Tokenizers 0.11.0
