metadata
language:
- sv
- 'no'
- da
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
- mozilla-foundation/common_voice_11_0
- mozilla-foundation/common_voice_11_0
- babelbox/babelbox_voice
- NbAiLab/NST
- NbAiLab/NPSC
- google/fleurs
- google/fleurs
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper Medium Nordic
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_11_0
type: mozilla-foundation/common_voice_11_0
config: sv-SE
split: test
metrics:
- name: Wer
type: wer
value: 11.307923879152778
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: babelbox/babelbox_voice
type: babelbox/babelbox_voice
metrics:
- name: Wer
type: wer
value: 11.307923879152778
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: NbAiLab/NST
type: NbAiLab/NST
metrics:
- name: Wer
type: wer
value: 11.307923879152778
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: NbAiLab/NPSC
type: NbAiLab/NPSC
metrics:
- name: Wer
type: wer
value: 11.307923879152778
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: google/fleurs
type: google/fleurs
metrics:
- name: Wer
type: wer
value: 11.307923879152778
Whisper Medium Nordic
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0, the mozilla-foundation/common_voice_11_0, the mozilla-foundation/common_voice_11_0, the babelbox/babelbox_voice, the NbAiLab/NST, the NbAiLab/NPSC, the google/fleurs, the google/fleurs and the google/fleurs datasets. It achieves the following results on the evaluation set:
- Loss: 0.2129
- Wer: 11.3079
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-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.3056 | 0.1 | 1000 | 0.2670 | 99.9221 |
0.16 | 0.2 | 2000 | 0.2322 | 99.6640 |
0.1309 | 0.3 | 3000 | 0.2152 | 98.9759 |
0.097 | 0.4 | 4000 | 0.2112 | 100.0 |
0.091 | 0.5 | 5000 | 0.2094 | 99.7312 |
0.1098 | 0.6 | 6000 | 0.2098 | 98.6077 |
0.0637 | 0.7 | 7000 | 0.2148 | 98.4625 |
0.0718 | 0.8 | 8000 | 0.2151 | 99.8710 |
0.0517 | 0.9 | 9000 | 0.2175 | 97.2342 |
0.0465 | 1.0 | 10000 | 0.2129 | 96.3552 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2