|
---
|
|
language:
|
|
- sv-SE
|
|
license: apache-2.0
|
|
tags:
|
|
- automatic-speech-recognition
|
|
- mozilla-foundation/common_voice_7_0
|
|
- generated_from_trainer
|
|
- no
|
|
- robust-speech-event
|
|
- model_for_talk
|
|
datasets:
|
|
- mozilla-foundation/common_voice_7_0
|
|
model-index:
|
|
- name: XLS-R-300M-LM - Norwegian
|
|
results:
|
|
- task:
|
|
name: Automatic Speech Recognition
|
|
type: automatic-speech-recognition
|
|
dataset:
|
|
name: NPSC
|
|
type: NbAiLab/NPSC
|
|
args: sv-SE
|
|
metrics:
|
|
- name: Eval WER
|
|
type: wer
|
|
value: 21.10
|
|
- name: Eval CER
|
|
type: cer
|
|
value: 0.06
|
|
|
|
---
|
|
|
|
# XLS-R-300M-LM - Norwegian
|
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
|
|
### Scores without Language Model
|
|
Without using a language model, it achieves the following scores on the NPSC Eval set
|
|
It achieves the following results on the evaluation set without a language model:
|
|
- Loss: 0.1992
|
|
- WER: 0.2110
|
|
- CER: 0.0622
|
|
|
|
### Scores with Language Model
|
|
A 5-gram KenLM was added to boost the models performance. After
|
|
|
|
## Model description
|
|
This current version is based on checkpoint 8500 of [NbAiLab/wav2vec2-xlsr-300M-NPSC-OH](https://huggingface.co/NbAiLab/wav2vec2-xlsr-300M-NPSC-OH)
|
|
|
|
## Intended uses & limitations
|
|
Demo version only. The model will be updated later this week.
|
|
|
|
## Training and evaluation data
|
|
The model is trained and evaluated on [NPSC](https://huggingface.co/datasets/NbAiLab/NPSC). Unfortunately there is no Norwegian test data in Common Voice, and currently the model is only evaluated on the validation set of NPSC..
|
|
|
|
## Training procedure
|
|
### Training hyperparameters
|
|
The following hyperparameters were used during training:
|
|
- learning_rate: 7.5e-05
|
|
- train_batch_size: 8
|
|
- eval_batch_size: 8
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 4
|
|
- 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: 2000
|
|
- num_epochs: 30.0 (But interrupted after 8500 steps, approx 6 epochs)
|
|
- mixed_precision_training: Native AMP
|
|
|
|
|
|
|
