patrickvonplaten
commited on
Commit
•
24f2219
1
Parent(s):
ba22605
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 |
- task:
|
32 |
name: Automatic Speech Recognition
|
33 |
type: automatic-speech-recognition
|
@@ -51,8 +51,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
51 |
|
52 |
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 - SV-SE dataset.
|
53 |
It achieves the following results on the evaluation set:
|
|
|
54 |
- Loss: 0.3171
|
55 |
-
- Wer: 0.
|
56 |
|
57 |
## Model description
|
58 |
|
@@ -176,6 +177,6 @@ transcription = processor.batch_decode(logits.numpy()).text
|
|
176 |
|
177 |
| Without LM | With LM (run `./eval.py`) |
|
178 |
|---|---|
|
179 |
-
|
|
180 |
|
181 |
|
|
|
24 |
metrics:
|
25 |
- name: Test WER
|
26 |
type: wer
|
27 |
+
value: 16.98
|
28 |
- name: Test CER
|
29 |
type: cer
|
30 |
+
value: 5.66
|
31 |
- task:
|
32 |
name: Automatic Speech Recognition
|
33 |
type: automatic-speech-recognition
|
|
|
51 |
|
52 |
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 - SV-SE dataset.
|
53 |
It achieves the following results on the evaluation set:
|
54 |
+
|
55 |
- Loss: 0.3171
|
56 |
+
- Wer: 0.2468
|
57 |
|
58 |
## Model description
|
59 |
|
|
|
177 |
|
178 |
| Without LM | With LM (run `./eval.py`) |
|
179 |
|---|---|
|
180 |
+
| 24.68 | 16.98 |
|
181 |
|
182 |
|