metadata
license: apache-2.0
base_model: facebook/wav2vec2-base-960h
tags:
- generated_from_trainer
datasets:
- ami
metrics:
- wer
model-index:
- name: my_awesome_asr_mind_model
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: ami
type: ami
config: ihm
split: None
args: ihm
metrics:
- name: Wer
type: wer
value: 0.2439744220363994
my_awesome_asr_mind_model
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the ami dataset. It achieves the following results on the evaluation set:
- Loss: 0.9699
- Wer: 0.2440
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9924 | 20.0 | 1000 | 2.4484 | 0.2986 |
| 0.6182 | 40.0 | 2000 | 1.1429 | 0.2735 |
| 0.4255 | 60.0 | 3000 | 0.9063 | 0.2459 |
| 0.396 | 80.0 | 4000 | 0.9699 | 0.2440 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1
- Datasets 2.20.0
- Tokenizers 0.19.1