chani-polak

whisper-hebrew-chani

Deploy Dedicated

README

License: apache-2.0

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-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 20
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Table with columns: Training Loss, Epoch, Step, Validation Loss, Wer
Training Loss	Epoch	Step	Validation Loss	Wer
1.7775	0.5479	200	0.8552	0.5939
1.2913	1.0959	400	0.7857	0.5666
1.1373	1.6438	600	0.7515	0.5563
0.9639

Framework versions

Transformers 5.12.0
Pytorch 2.11.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

chani-polak

Model Tree

Base

openai/whisper-base

Fine-tuned

this model

Input Modalities

Audio

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

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-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 20
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Table with columns: Training Loss, Epoch, Step, Validation Loss, Wer
Training Loss	Epoch	Step	Validation Loss	Wer
1.7775	0.5479	200	0.8552	0.5939
1.2913	1.0959	400	0.7857	0.5666
1.1373	1.6438	600	0.7515	0.5563
0.9639

Framework versions

Transformers 5.12.0
Pytorch 2.11.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2