|
--- |
|
license: mit |
|
|
|
tags: |
|
- automatic-speech-recognition |
|
- common_voice |
|
|
|
datasets: |
|
- common_voice |
|
|
|
model-index: |
|
- name: wav2vec2-xls-r-300m-uk |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# wav2vec2-xlsr-53-300m-mls-german-ft |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the Common Voice 7.0 dataset. |
|
|
|
It achieves the following results on the evaluation set: |
|
|
|
- Loss: 0.2219 |
|
|
|
- Wer: 0.1288 |
|
|
|
## Model description |
|
More information needed |
|
|
|
## Intended uses & limitations |
|
More information needed |
|
|
|
## Training and evaluation data |
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
More information needed |
|
|
|
### Training results |
|
|
|
| Step | Training Loss | Validation Loss | Wer | |
|
|:-------:|:-------------:|:---------------:|:------:| |
|
| 4000 | 0.363600 | 0.211314 | 0.305 | |
|
| 10000 | 0.250800 | 0.178876 | 0.223011 | |
|
| 18000 | 0.187000 |0.163607 | 0.194422 | |
|
| 27200 | 0.155100 | 0.153098 | 0.168595 | |
|
| 39600 | 0.125600 | 0.141007 | 0.152833 | |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.11 |
|
- Pytorch 1.10.0 |
|
- Datasets 1.13 |
|
|
|
|
|
|
