metadata
license: cc-by-nc-4.0
base_model: utter-project/mHuBERT-147
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
metrics:
- wer
model-index:
- name: mHuBERT-147-upper-sorbian
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_17_0
type: common_voice_17_0
config: hsb
split: validation
args: hsb
metrics:
- name: Wer
type: wer
value: 1
mHuBERT-147-upper-sorbian
This model is a fine-tuned version of utter-project/mHuBERT-147 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 3.3582
- Wer: 1.0
- Cer: 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 15.5448 | 3.9216 | 100 | 16.7511 | 1.0 | 2.0768 |
| 10.1433 | 7.8431 | 200 | 10.5841 | 1.0 | 1.0 |
| 8.264 | 11.7647 | 300 | 8.8218 | 1.0 | 1.0 |
| 7.9924 | 15.6863 | 400 | 8.2091 | 1.0 | 1.0 |
| 7.1304 | 19.6078 | 500 | 7.5249 | 1.0 | 1.0 |
| 6.2453 | 23.5294 | 600 | 6.8211 | 1.0 | 1.0 |
| 6.2833 | 27.4510 | 700 | 6.1921 | 1.0 | 1.0 |
| 5.3658 | 31.3725 | 800 | 5.6396 | 1.0 | 1.0 |
| 4.8314 | 35.2941 | 900 | 5.1645 | 1.0 | 1.0 |
| 4.8285 | 39.2157 | 1000 | 4.7647 | 1.0 | 1.0 |
| 4.2474 | 43.1373 | 1100 | 4.4360 | 1.0 | 1.0 |
| 3.9898 | 47.0588 | 1200 | 4.1735 | 1.0 | 1.0 |
| 3.8997 | 50.9804 | 1300 | 3.9678 | 1.0 | 1.0 |
| 3.7723 | 54.9020 | 1400 | 3.8085 | 1.0 | 1.0 |
| 3.6148 | 58.8235 | 1500 | 3.6879 | 1.0 | 1.0 |
| 3.4969 | 62.7451 | 1600 | 3.5966 | 1.0 | 1.0 |
| 3.5233 | 66.6667 | 1700 | 3.5286 | 1.0 | 1.0 |
| 3.4324 | 70.5882 | 1800 | 3.4771 | 1.0 | 1.0 |
| 3.393 | 74.5098 | 1900 | 3.4387 | 1.0 | 1.0 |
| 3.3967 | 78.4314 | 2000 | 3.4102 | 1.0 | 1.0 |
| 3.3846 | 82.3529 | 2100 | 3.3891 | 1.0 | 1.0 |
| 3.3431 | 86.2745 | 2200 | 3.3746 | 1.0 | 1.0 |
| 3.3601 | 90.1961 | 2300 | 3.3653 | 1.0 | 1.0 |
| 3.3545 | 94.1176 | 2400 | 3.3599 | 1.0 | 1.0 |
| 3.3114 | 98.0392 | 2500 | 3.3582 | 1.0 | 1.0 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1