Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: gpl-3.0
|
| 3 |
|
| 4 |
-
library_name: generic
|
| 5 |
-
|
| 6 |
language:
|
| 7 |
- be
|
| 8 |
|
|
@@ -54,4 +52,13 @@ i.e. enlarge mentioned splits.
|
|
| 54 |
Language model was built using [KenLM](https://kheafield.com/code/kenlm/estimation/).
|
| 55 |
5-gram Language model was built on sentences from `Train + (Other - Dev - Test)` splits of `mozilla-foundation/common_voice_8_0 be` dataset.
|
| 56 |
|
| 57 |
-
Source code is available [here](https://github.com/yks72p/stt_be).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: gpl-3.0
|
| 3 |
|
|
|
|
|
|
|
| 4 |
language:
|
| 5 |
- be
|
| 6 |
|
|
|
|
| 52 |
Language model was built using [KenLM](https://kheafield.com/code/kenlm/estimation/).
|
| 53 |
5-gram Language model was built on sentences from `Train + (Other - Dev - Test)` splits of `mozilla-foundation/common_voice_8_0 be` dataset.
|
| 54 |
|
| 55 |
+
Source code is available [here](https://github.com/yks72p/stt_be).
|
| 56 |
+
|
| 57 |
+
## Run model in a browser
|
| 58 |
+
|
| 59 |
+
This page contains interactive demo widget that lets you test this model right in a browser.
|
| 60 |
+
|
| 61 |
+
However, this widget uses Acoustic model only **without** Language model that significantly improves overall performance.
|
| 62 |
+
|
| 63 |
+
You can play with **full pipeline of Acoustic model + Language model** on the following [spaces page](https://huggingface.co/spaces/ales/wav2vec2-cv-be-lm/tree/main)
|
| 64 |
+
(also works from browser).
|