Correctness regression¶
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
---|---|---|---|---|
Overall Score |
88.9% passed tests (8 passed / 1 failed). |
88.9% passed tests (8 passed / 1 failed). |
66.7% passed tests (6 passed / 3 failed). |
66.7% passed tests (6 passed / 3 failed). |
Concordance Correlation Coeff¶
Data |
Concordance Correlation Coeff |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.66 |
0.65 |
0.64 |
0.65 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.72 |
0.74 |
0.75 |
0.72 |
msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard |
0.50 |
0.50 |
0.43 |
0.49 |
mean |
0.63 |
0.63 |
0.61 |
0.62 |
Mean Absolute Error¶
Data |
Mean Absolute Error |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.12 |
0.11 |
0.13 |
0.12 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.09 |
0.09 |
0.09 |
0.10 |
msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard |
0.10 |
0.09 |
0.12 |
0.10 |
mean |
0.10 |
0.10 |
0.11 |
0.11 |
Pearson Correlation Coeff¶
Data |
Pearson Correlation Coeff |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.66 |
0.65 |
0.70 |
0.66 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.73 |
0.74 |
0.75 |
0.73 |
msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard |
0.51 |
0.50 |
0.55 |
0.50 |
mean |
0.63 |
0.63 |
0.67 |
0.63 |
Visualization¶
w2v2-L |
hubert-L |
wavlm |
data2vec |
---|---|---|---|