Commit
·
b4ddd85
1
Parent(s):
6abd91b
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,6 +41,12 @@ model-index:
|
|
| 41 |
---
|
| 42 |
# XLS-R-1B-ITALIAN-DOC4LM-5GRAM
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
## Language model information
|
| 45 |
|
| 46 |
Our language model was generated using a dataset of Italian wikipedia articles and manual transcriptions of radio newspapers and television programs.
|
|
|
|
| 41 |
---
|
| 42 |
# XLS-R-1B-ITALIAN-DOC4LM-5GRAM
|
| 43 |
|
| 44 |
+
## Fine-tuned XLS-R 1B model for speech recognition in Italian
|
| 45 |
+
|
| 46 |
+
Fine-tuned [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on Italian using the train and validation splits of [Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0), [Multilingual TEDx](http://www.openslr.org/100), [Multilingual LibriSpeech](https://www.openslr.org/94/), and [Voxpopuli](https://github.com/facebookresearch/voxpopuli).
|
| 47 |
+
When using this model, make sure that your speech input is sampled at 16kHz.
|
| 48 |
+
|
| 49 |
+
|
| 50 |
## Language model information
|
| 51 |
|
| 52 |
Our language model was generated using a dataset of Italian wikipedia articles and manual transcriptions of radio newspapers and television programs.
|