README.md

metadata

language:
  - multilingual
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: model trenovan na en setu, nastaveni jazyka en
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: xbilek25/train_set_1st_1000_de_en_de
          type: mozilla-foundation/common_voice_11_0
          args: 'config: ende, split: train'
        metrics:
          - name: Wer
            type: wer
            value: 19.711821211527152

model trenovan na en setu, nastaveni jazyka en

This model is a fine-tuned version of openai/whisper-medium on the xbilek25/train_set_1st_1000_de_en_de dataset. It achieves the following results on the evaluation set:

• Loss: 0.2246
• Wer: 19.7118

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0895	1.25	1000	0.2036	22.3976
0.0071	3.25	2000	0.2246	19.7118

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2