Commit
•
47398e8
1
Parent(s):
c0c2c5c
Update README.md
Browse files
README.md
CHANGED
@@ -24,10 +24,10 @@ model-index:
|
|
24 |
metrics:
|
25 |
- name: Test WER
|
26 |
type: wer
|
27 |
-
value:
|
28 |
- name: Test CER
|
29 |
type: cer
|
30 |
-
value:
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -35,24 +35,21 @@ should probably proofread and complete it, then remove this comment. -->
|
|
35 |
|
36 |
# wav2vec2-large-xls-r-300m-hsb-v2
|
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
|
39 |
It achieves the following results on the evaluation set:
|
40 |
- Loss: 0.5328
|
41 |
- Wer: 0.4596
|
42 |
|
43 |
-
|
44 |
|
45 |
-
|
46 |
|
47 |
-
|
48 |
|
49 |
-
|
50 |
|
51 |
-
|
52 |
|
53 |
-
More information needed
|
54 |
-
|
55 |
-
## Training procedure
|
56 |
|
57 |
### Training hyperparameters
|
58 |
|
|
|
24 |
metrics:
|
25 |
- name: Test WER
|
26 |
type: wer
|
27 |
+
value: 0.4654228855721393
|
28 |
- name: Test CER
|
29 |
type: cer
|
30 |
+
value: 0.11351049990708047
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
# wav2vec2-large-xls-r-300m-hsb-v2
|
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_8_0 - HSB dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
- Loss: 0.5328
|
41 |
- Wer: 0.4596
|
42 |
|
43 |
+
### Evaluation Commands
|
44 |
|
45 |
+
1. To evaluate on mozilla-foundation/common_voice_8_0 with test split
|
46 |
|
47 |
+
python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-hsb-v2 --dataset mozilla-foundation/common_voice_8_0 --config hsb --split test --log_outputs
|
48 |
|
49 |
+
2. To evaluate on speech-recognition-community-v2/dev_data
|
50 |
|
51 |
+
Upper Sorbian (hsb) not found in speech-recognition-community-v2/dev_data
|
52 |
|
|
|
|
|
|
|
53 |
|
54 |
### Training hyperparameters
|
55 |
|