Correctness regression¶
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
---|---|---|---|---|
Overall Score |
66.7% passed tests (6 passed / 3 failed). |
55.6% passed tests (5 passed / 4 failed). |
55.6% passed tests (5 passed / 4 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 |
0.51 |
0.49 |
0.55 |
0.54 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.63 |
0.66 |
0.67 |
0.62 |
msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard |
0.46 |
0.44 |
0.41 |
0.44 |
mean |
0.53 |
0.53 |
0.54 |
0.53 |
Mean Absolute Error¶
Data |
Mean Absolute Error |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.14 |
0.14 |
0.15 |
0.14 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.08 |
0.08 |
0.08 |
0.09 |
msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard |
0.08 |
0.08 |
0.10 |
0.09 |
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 |
0.53 |
0.51 |
0.59 |
0.55 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.64 |
0.66 |
0.68 |
0.64 |
msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard |
0.46 |
0.45 |
0.48 |
0.45 |
mean |
0.54 |
0.54 |
0.58 |
0.55 |
Visualization¶
w2v2-L |
hubert-L |
wavlm |
data2vec |
---|---|---|---|