Update README.md
Browse files
README.md
CHANGED
@@ -31,6 +31,8 @@ model-index:
|
|
31 |
|
32 |
# Ukrainian STT model (with Language Model)
|
33 |
|
|
|
|
|
34 |
Have a look on the better model with more parameters: https://huggingface.co/Yehor/wav2vec2-xls-r-1b-uk-with-lm
|
35 |
|
36 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UK dataset.
|
@@ -41,21 +43,19 @@ It achieves the following results on the evaluation set:
|
|
41 |
|
42 |
The above results present evaluation without the language model.
|
43 |
|
44 |
-
Follow our community in Telegram: https://t.me/speech_recognition_uk
|
45 |
-
|
46 |
## Model description
|
47 |
|
48 |
On 100 test example the model shows the following results:
|
49 |
|
50 |
Without LM:
|
51 |
|
52 |
-
- WER: 0.
|
53 |
-
- CER: 0.
|
54 |
|
55 |
With LM:
|
56 |
|
57 |
-
- WER: 0.
|
58 |
-
- CER: 0.
|
59 |
|
60 |
|
61 |
## Training procedure
|
|
|
31 |
|
32 |
# Ukrainian STT model (with Language Model)
|
33 |
|
34 |
+
🇺🇦 Join Ukrainian Speech Recognition Community - https://t.me/speech_recognition_uk
|
35 |
+
|
36 |
Have a look on the better model with more parameters: https://huggingface.co/Yehor/wav2vec2-xls-r-1b-uk-with-lm
|
37 |
|
38 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UK dataset.
|
|
|
43 |
|
44 |
The above results present evaluation without the language model.
|
45 |
|
|
|
|
|
46 |
## Model description
|
47 |
|
48 |
On 100 test example the model shows the following results:
|
49 |
|
50 |
Without LM:
|
51 |
|
52 |
+
- WER: 0.2647
|
53 |
+
- CER: 0.0469
|
54 |
|
55 |
With LM:
|
56 |
|
57 |
+
- WER: 0.1568
|
58 |
+
- CER: 0.0289
|
59 |
|
60 |
|
61 |
## Training procedure
|