|
--- |
|
library_name: nemo |
|
license: mit |
|
language: |
|
- fa |
|
metrics: |
|
- wer |
|
pipeline_tag: automatic-speech-recognition |
|
tags: |
|
- audio |
|
- speech |
|
- automatic-speech-recognition |
|
model-index: |
|
- name: Wav2Vec2 XLS-R 300M Persian (Farsi) by Ali Farokh |
|
results: |
|
- task: |
|
name: Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: Common Voice fa |
|
type: common_voice |
|
args: fa |
|
metrics: |
|
- name: Test WER |
|
type: wer |
|
value: 32.08 |
|
--- |
|
|
|
# NeMo Conformer Medium Persian (Farsi) |
|
Please refer to [Persian ASR](https://github.com/alifarrokh/persian-asr) for more information about training and using this model. |
