Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
temp
This model is a fine-tuned version of openai/whisper-large-v2 on the common_voice_14_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2796
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.6335 | 1.0 | 47090 | 0.3652 |
0.5913 | 2.0 | 94180 | 0.2796 |
Framework versions
- PEFT 0.11.2.dev0
- Transformers 4.43.0.dev0
- Pytorch 2.2.0
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 267
Model tree for Jaafarulloh/stt_new_uzbek
Base model
openai/whisper-large-v2
Adapter
this model