Created model card for first successfull training.
Browse filesHopefully now that I got it training with the dataset I can try again training the model.
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
language: nah specifically ncj
|
4 |
+
datasets:
|
5 |
+
- created a new dataset based on https://www.openslr.org/92/
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
tags:
|
9 |
+
- audio
|
10 |
+
- automatic-speech-recognition
|
11 |
+
- speech
|
12 |
+
- xlsr-fine-tuning-week
|
13 |
+
license: apache-2.0
|
14 |
+
model-index:
|
15 |
+
- name: Nahuatl XLSR Wav2Vec 53
|
16 |
+
results:
|
17 |
+
- task:
|
18 |
+
name: Speech Recognition
|
19 |
+
type: automatic-speech-recognition
|
20 |
+
metrics:
|
21 |
+
- name: Test WER
|
22 |
+
type: wer
|
23 |
+
value: 69.11
|
24 |
+
---
|
25 |
+
|
26 |
+
First full try on the new dataset. Updates to come.
|