README.md

metadata

language:
  - tr
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - a
metrics:
  - wer
model-index:
  - name: mms tr
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: a
          type: a
          config: default
          split: train
          args: 'config: tr, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 1

mms tr

This model is a fine-tuned version of facebook/mms-1b-all on the a dataset. It achieves the following results on the evaluation set:

• Loss: 93.8163
• 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: 1
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.33	1	169.9452	1.0
No log	0.67	2	115.9592	1.0
No log	1.0	3	93.8163	1.0

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0