Correctness regression¶
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
---|---|---|---|---|
Overall Score |
0.0% passed tests (0 passed / 9 failed). |
22.2% passed tests (2 passed / 7 failed). |
44.4% passed tests (4 passed / 5 failed). |
33.3% passed tests (3 passed / 6 failed). |
Concordance Correlation Coeff¶
Data |
Concordance Correlation Coeff |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.39 |
0.45 |
0.51 |
0.43 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.42 |
0.64 |
0.65 |
0.62 |
msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard |
0.17 |
0.37 |
0.37 |
0.37 |
mean |
0.32 |
0.49 |
0.51 |
0.47 |
Mean Absolute Error¶
Data |
Mean Absolute Error |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.17 |
0.16 |
0.15 |
0.16 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.13 |
0.11 |
0.11 |
0.11 |
msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard |
0.12 |
0.10 |
0.12 |
0.10 |
mean |
0.14 |
0.12 |
0.13 |
0.12 |
Pearson Correlation Coeff¶
Data |
Pearson Correlation Coeff |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.43 |
0.49 |
0.55 |
0.47 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.42 |
0.64 |
0.66 |
0.62 |
msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard |
0.20 |
0.38 |
0.44 |
0.37 |
mean |
0.35 |
0.50 |
0.55 |
0.49 |
Visualization¶
w2v2-L |
hubert-L |
wavlm |
data2vec |
---|---|---|---|