Update readme language code and referral to new model
Browse files
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
-
language: sv
|
| 3 |
datasets:
|
| 4 |
- common_voice
|
| 5 |
-
-
|
| 6 |
metrics:
|
| 7 |
- wer
|
| 8 |
- cer
|
|
@@ -36,6 +36,8 @@ model-index:
|
|
| 36 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Swedish using the [NST Swedish Dictation](https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-17/).
|
| 37 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
| 38 |
|
|
|
|
|
|
|
| 39 |
## Usage
|
| 40 |
|
| 41 |
The model can be used directly (without a language model) as follows:
|
|
|
|
| 1 |
---
|
| 2 |
+
language: sv
|
| 3 |
datasets:
|
| 4 |
- common_voice
|
| 5 |
+
- KTH/nst
|
| 6 |
metrics:
|
| 7 |
- wer
|
| 8 |
- cer
|
|
|
|
| 36 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Swedish using the [NST Swedish Dictation](https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-17/).
|
| 37 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
| 38 |
|
| 39 |
+
**Note:** We commend using our newer model [wav2vec2-large-voxrex-swedish](https://huggingface.co/KBLab/wav2vec2-large-voxrex-swedish) for the best performance.
|
| 40 |
+
|
| 41 |
## Usage
|
| 42 |
|
| 43 |
The model can be used directly (without a language model) as follows:
|