French_asr_model / README.md
Ponyyyy's picture
End of training
a1ed6d7 verified
|
raw
history blame
1.93 kB
---
license: apache-2.0
base_model: jonatasgrosman/wav2vec2-large-xlsr-53-french
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- wer
model-index:
- name: French_asr_model
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: minds14
type: minds14
config: fr-FR
split: None
args: fr-FR
metrics:
- name: Wer
type: wer
value: 0.3484848484848485
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# French_asr_model
This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-french](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-french) on the minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2408
- Wer: 0.3485
## 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: 0.0001
- 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: 250
- training_steps: 1000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:--------:|:----:|:---------------:|:------:|
| 0.0049 | 333.3333 | 500 | 1.1485 | 0.3485 |
| 0.0015 | 666.6667 | 1000 | 1.2408 | 0.3485 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1