metadata
base_model: facebook/mms-1b-all
datasets:
- common_voice_17_0
library_name: transformers
license: cc-by-nc-4.0
metrics:
- wer
- bleu
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-mms-1b-CV17.0-training_set_variations
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: common_voice_17_0
type: common_voice_17_0
config: ta
split: validation
args: ta
metrics:
- type: wer
value: 0.9963132675846669
name: Wer
- type: bleu
value: 0
name: Bleu
wav2vec2-mms-1b-CV17.0-training_set_variations
This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 2.4706
- Wer: 0.9963
- Cer: 0.6333
- Bleu: 0.0
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: 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_ratio: 0.15
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Bleu |
|---|---|---|---|---|---|---|
| 8.3205 | 6.25 | 100 | 3.8395 | 1.0415 | 0.8830 | 0.0 |
| 3.3463 | 12.5 | 200 | 3.2263 | 1.0230 | 0.8113 | 0.0 |
| 3.0206 | 18.75 | 300 | 3.0363 | 1.0047 | 0.8167 | 0.0 |
| 2.7973 | 25.0 | 400 | 2.8782 | 1.0023 | 0.7764 | 0.0 |
| 2.4269 | 31.25 | 500 | 2.6308 | 1.0027 | 0.6957 | 0.0 |
| 2.0251 | 37.5 | 600 | 2.4706 | 0.9963 | 0.6333 | 0.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1