Upload smoke_A_baseline

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,15 @@
+---
+tags:
+- voiceclap
+- checkpoint
+---
+
+# smoke_A_baseline
+
+Training run from the VoiceCLAP experiments: final weights plus the run's configs and evaluation results. Intermediate epochs, optimizer state and logs are not included. Local filesystem paths in config files have been shortened.
+
+12 files, 2.9 GB. Index of all runs: [VoiceNetCkpt/voiceclap-checkpoints-index](https://huggingface.co/VoiceNetCkpt/voiceclap-checkpoints-index).
+
+Weights:
+
+- `checkpoints/epoch_latest.pt`

checkpoints/epoch_latest.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060c4c2c95f689e8d15edb80b7203ff11b7f9562ee7eaf276d055446d0256120
+size 2938445690

emonet_voice_results/epoch_1/emonet_voice.json

@@ -0,0 +1,228 @@
+{
+  "model": "CLAPNaFlex-base-ModernBERT",
+  "pretrained": "epoch_1.pt",
+  "model_type": "clap_v2",
+  "task": "emonet_voice",
+  "dataset": "t1a5anu-anon/emonet-voice-bench",
+  "split": "train",
+  "n_samples": 12600,
+  "n_classes": 42,
+  "classes": [
+    "Affection",
+    "Amusement",
+    "Anger",
+    "Arousal",
+    "Astonishment",
+    "Authenticity",
+    "Awe",
+    "Bitterness",
+    "Concentration",
+    "Confusion",
+    "Contemplation",
+    "Contempt",
+    "Contentment",
+    "Disappointment",
+    "Disgust",
+    "Distress",
+    "Doubt",
+    "Elation",
+    "Embarrassment",
+    "Emotional%20Numbness",
+    "Fatigue",
+    "Fear",
+    "Helplessness",
+    "Hope",
+    "Impatience%20and%20Irritability",
+    "Infatuation",
+    "Interest",
+    "Intoxication",
+    "Jealousy%20%26%20Envy",
+    "Longing",
+    "Malevolence",
+    "Pain",
+    "Pleasure",
+    "Pride",
+    "Relief",
+    "Sadness",
+    "Sexual%20Lust",
+    "Shame",
+    "Sourness",
+    "Teasing",
+    "Thankfulness",
+    "Triumph"
+  ],
+  "n_templates": 5,
+  "metrics": {
+    "acc1": 0.02365079365079365
+  },
+  "per_class": {
+    "Affection": {
+      "n": 300,
+      "acc": 0.0033333333333333335
+    },
+    "Amusement": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Anger": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Arousal": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Astonishment": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Authenticity": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Awe": {
+      "n": 300,
+      "acc": 0.01
+    },
+    "Bitterness": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Concentration": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Confusion": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Contemplation": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Contempt": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Contentment": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Disappointment": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Disgust": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Distress": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Doubt": {
+      "n": 300,
+      "acc": 0.006666666666666667
+    },
+    "Elation": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Embarrassment": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Emotional%20Numbness": {
+      "n": 300,
+      "acc": 0.013333333333333334
+    },
+    "Fatigue": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Fear": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Helplessness": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Hope": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Impatience%20and%20Irritability": {
+      "n": 300,
+      "acc": 0.8666666666666667
+    },
+    "Infatuation": {
+      "n": 300,
+      "acc": 0.006666666666666667
+    },
+    "Interest": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Intoxication": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Jealousy%20%26%20Envy": {
+      "n": 300,
+      "acc": 0.03
+    },
+    "Longing": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Malevolence": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Pain": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Pleasure": {
+      "n": 300,
+      "acc": 0.02666666666666667
+    },
+    "Pride": {
+      "n": 300,
+      "acc": 0.013333333333333334
+    },
+    "Relief": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Sadness": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Sexual%20Lust": {
+      "n": 300,
+      "acc": 0.016666666666666666
+    },
+    "Shame": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Sourness": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Teasing": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Thankfulness": {
+      "n": 300,
+      "acc": 0.0
+    },
+    "Triumph": {
+      "n": 300,
+      "acc": 0.0
+    }
+  }
+}

maeb_voice_results/epoch_1/open_clap__CLAPNaFlex-base-ModernBERT/epoch_1/CommonLanguageAgeDetection.json

@@ -0,0 +1,140 @@
+{
+  "dataset_revision": "a9c585af68d65a29c4ad12121f83853fa1cdda92",
+  "task_name": "CommonLanguageAgeDetection",
+  "mteb_version": "2.10.9",
+  "scores": {
+    "test": [
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.084,
+            "f1": 0.072786,
+            "f1_weighted": 0.100064,
+            "precision": 0.115335,
+            "precision_weighted": 0.233652,
+            "recall": 0.104155,
+            "recall_weighted": 0.084,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.1165,
+            "f1": 0.066904,
+            "f1_weighted": 0.150635,
+            "precision": 0.110315,
+            "precision_weighted": 0.29076,
+            "recall": 0.068167,
+            "recall_weighted": 0.1165,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.1325,
+            "f1": 0.058173,
+            "f1_weighted": 0.150962,
+            "precision": 0.110528,
+            "precision_weighted": 0.316668,
+            "recall": 0.09021,
+            "recall_weighted": 0.1325,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.0605,
+            "f1": 0.052848,
+            "f1_weighted": 0.059465,
+            "precision": 0.126987,
+            "precision_weighted": 0.335121,
+            "recall": 0.091143,
+            "recall_weighted": 0.0605,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.1655,
+            "f1": 0.095933,
+            "f1_weighted": 0.198545,
+            "precision": 0.110733,
+            "precision_weighted": 0.262762,
+            "recall": 0.098349,
+            "recall_weighted": 0.1655,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.167,
+            "f1": 0.083955,
+            "f1_weighted": 0.16479,
+            "precision": 0.116304,
+            "precision_weighted": 0.30189,
+            "recall": 0.130125,
+            "recall_weighted": 0.167,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.096,
+            "f1": 0.052451,
+            "f1_weighted": 0.124777,
+            "precision": 0.102591,
+            "precision_weighted": 0.303889,
+            "recall": 0.069834,
+            "recall_weighted": 0.096,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.2085,
+            "f1": 0.106305,
+            "f1_weighted": 0.232602,
+            "precision": 0.132893,
+            "precision_weighted": 0.314803,
+            "recall": 0.105509,
+            "recall_weighted": 0.2085,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.0935,
+            "f1": 0.053135,
+            "f1_weighted": 0.098839,
+            "precision": 0.093342,
+            "precision_weighted": 0.242287,
+            "recall": 0.094916,
+            "recall_weighted": 0.0935,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.15,
+            "f1": 0.052821,
+            "f1_weighted": 0.136122,
+            "precision": 0.088365,
+            "precision_weighted": 0.262613,
+            "recall": 0.062587,
+            "recall_weighted": 0.15,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.1274,
+        "f1": 0.069531,
+        "f1_weighted": 0.14168,
+        "precision": 0.110739,
+        "precision_weighted": 0.286444,
+        "recall": 0.091499,
+        "recall_weighted": 0.1274,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.1274,
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ]
+      }
+    ]
+  },
+  "evaluation_time": 98.50806593894958,
+  "kg_co2_emissions": null,
+  "date": null
+}

maeb_voice_results/epoch_1/open_clap__CLAPNaFlex-base-ModernBERT/epoch_1/IEMOCAPGender.json

@@ -0,0 +1,85 @@
+{
+  "dataset_revision": "6d4225271da423e791e16770d335cfa351cdf88e",
+  "task_name": "IEMOCAPGender",
+  "mteb_version": "2.10.9",
+  "scores": {
+    "train": [
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.570717,
+            "f1": 0.56965,
+            "f1_weighted": 0.57076,
+            "precision": 0.569638,
+            "precision_weighted": 0.570807,
+            "recall": 0.569666,
+            "recall_weighted": 0.570717,
+            "ap": 0.565016,
+            "ap_weighted": 0.565016
+          },
+          {
+            "accuracy": 0.542331,
+            "f1": 0.538582,
+            "f1_weighted": 0.536055,
+            "precision": 0.552716,
+            "precision_weighted": 0.555333,
+            "recall": 0.549837,
+            "recall_weighted": 0.542331,
+            "ap": 0.558267,
+            "ap_weighted": 0.558267
+          },
+          {
+            "accuracy": 0.545319,
+            "f1": 0.54475,
+            "f1_weighted": 0.545744,
+            "precision": 0.545046,
+            "precision_weighted": 0.546927,
+            "recall": 0.545214,
+            "recall_weighted": 0.545319,
+            "ap": 0.555291,
+            "ap_weighted": 0.555291
+          },
+          {
+            "accuracy": 0.550797,
+            "f1": 0.544613,
+            "f1_weighted": 0.545405,
+            "precision": 0.551624,
+            "precision_weighted": 0.551567,
+            "recall": 0.549178,
+            "recall_weighted": 0.550797,
+            "ap": 0.520252,
+            "ap_weighted": 0.520252
+          },
+          {
+            "accuracy": 0.549576,
+            "f1": 0.548607,
+            "f1_weighted": 0.549847,
+            "precision": 0.548641,
+            "precision_weighted": 0.550303,
+            "recall": 0.548758,
+            "recall_weighted": 0.549576,
+            "ap": 0.556096,
+            "ap_weighted": 0.556096
+          }
+        ],
+        "accuracy": 0.551748,
+        "f1": 0.54924,
+        "f1_weighted": 0.549562,
+        "precision": 0.553533,
+        "precision_weighted": 0.554987,
+        "recall": 0.552531,
+        "recall_weighted": 0.551748,
+        "ap": 0.550985,
+        "ap_weighted": 0.550985,
+        "main_score": 0.551748,
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ]
+      }
+    ]
+  },
+  "evaluation_time": 187.25707149505615,
+  "kg_co2_emissions": null,
+  "date": null
+}

maeb_voice_results/epoch_1/open_clap__CLAPNaFlex-base-ModernBERT/epoch_1/MInDS14.json

@@ -0,0 +1,888 @@
+{
+  "dataset_revision": "58d73d2cddefab7df4bc0b814aa5c53c5fd4928e",
+  "task_name": "MInDS14",
+  "mteb_version": "2.10.9",
+  "scores": {
+    "train": [
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.07563,
+            "f1": 0.056859,
+            "f1_weighted": 0.058675,
+            "precision": 0.055567,
+            "precision_weighted": 0.057666,
+            "recall": 0.074186,
+            "recall_weighted": 0.07563,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.10084,
+            "f1": 0.076147,
+            "f1_weighted": 0.08509,
+            "precision": 0.109569,
+            "precision_weighted": 0.13085,
+            "recall": 0.097852,
+            "recall_weighted": 0.10084,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.076271,
+            "f1": 0.038679,
+            "f1_weighted": 0.046828,
+            "precision": 0.028995,
+            "precision_weighted": 0.035965,
+            "recall": 0.073214,
+            "recall_weighted": 0.076271,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.050847,
+            "f1": 0.023413,
+            "f1_weighted": 0.031075,
+            "precision": 0.018553,
+            "precision_weighted": 0.024873,
+            "recall": 0.03869,
+            "recall_weighted": 0.050847,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.059322,
+            "f1": 0.027081,
+            "f1_weighted": 0.029061,
+            "precision": 0.020059,
+            "precision_weighted": 0.021839,
+            "recall": 0.058081,
+            "recall_weighted": 0.059322,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.072582,
+        "f1": 0.044436,
+        "f1_weighted": 0.050146,
+        "precision": 0.046549,
+        "precision_weighted": 0.054239,
+        "recall": 0.068405,
+        "recall_weighted": 0.072582,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.072582,
+        "hf_subset": "en-GB",
+        "languages": [
+          "eng-Latn"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.037037,
+            "f1": 0.022381,
+            "f1_weighted": 0.024691,
+            "precision": 0.019405,
+            "precision_weighted": 0.023765,
+            "recall": 0.041667,
+            "recall_weighted": 0.037037,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.074074,
+            "f1": 0.044769,
+            "f1_weighted": 0.046674,
+            "precision": 0.041369,
+            "precision_weighted": 0.043089,
+            "recall": 0.074237,
+            "recall_weighted": 0.074074,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.037037,
+            "f1": 0.018543,
+            "f1_weighted": 0.020729,
+            "precision": 0.012925,
+            "precision_weighted": 0.015079,
+            "recall": 0.036054,
+            "recall_weighted": 0.037037,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.101852,
+            "f1": 0.056767,
+            "f1_weighted": 0.064426,
+            "precision": 0.068488,
+            "precision_weighted": 0.084178,
+            "recall": 0.099379,
+            "recall_weighted": 0.101852,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.084112,
+            "f1": 0.043281,
+            "f1_weighted": 0.047176,
+            "precision": 0.033901,
+            "precision_weighted": 0.037582,
+            "recall": 0.079932,
+            "recall_weighted": 0.084112,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.066822,
+        "f1": 0.037148,
+        "f1_weighted": 0.040739,
+        "precision": 0.035218,
+        "precision_weighted": 0.040739,
+        "recall": 0.066254,
+        "recall_weighted": 0.066822,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.066822,
+        "hf_subset": "fr-FR",
+        "languages": [
+          "fra-Latn"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.1,
+            "f1": 0.080171,
+            "f1_weighted": 0.078175,
+            "precision": 0.073667,
+            "precision_weighted": 0.070608,
+            "recall": 0.103375,
+            "recall_weighted": 0.1,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.064748,
+            "f1": 0.043233,
+            "f1_weighted": 0.039512,
+            "precision": 0.056538,
+            "precision_weighted": 0.04855,
+            "recall": 0.065726,
+            "recall_weighted": 0.064748,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.079137,
+            "f1": 0.049651,
+            "f1_weighted": 0.055018,
+            "precision": 0.046488,
+            "precision_weighted": 0.052632,
+            "recall": 0.073367,
+            "recall_weighted": 0.079137,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.064748,
+            "f1": 0.042554,
+            "f1_weighted": 0.037455,
+            "precision": 0.088715,
+            "precision_weighted": 0.073584,
+            "recall": 0.071627,
+            "recall_weighted": 0.064748,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.079137,
+            "f1": 0.059235,
+            "f1_weighted": 0.062403,
+            "precision": 0.058209,
+            "precision_weighted": 0.063733,
+            "recall": 0.080322,
+            "recall_weighted": 0.079137,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.077554,
+        "f1": 0.054969,
+        "f1_weighted": 0.054512,
+        "precision": 0.064723,
+        "precision_weighted": 0.061821,
+        "recall": 0.078883,
+        "recall_weighted": 0.077554,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.077554,
+        "hf_subset": "it-IT",
+        "languages": [
+          "ita-Latn"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.05102,
+            "f1": 0.022436,
+            "f1_weighted": 0.01753,
+            "precision": 0.013961,
+            "precision_weighted": 0.011039,
+            "recall": 0.071429,
+            "recall_weighted": 0.05102,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.061856,
+            "f1": 0.029815,
+            "f1_weighted": 0.027303,
+            "precision": 0.022321,
+            "precision_weighted": 0.019545,
+            "recall": 0.060317,
+            "recall_weighted": 0.061856,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.072165,
+            "f1": 0.037086,
+            "f1_weighted": 0.050837,
+            "precision": 0.035231,
+            "precision_weighted": 0.04864,
+            "recall": 0.052381,
+            "recall_weighted": 0.072165,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.082474,
+            "f1": 0.048928,
+            "f1_weighted": 0.057758,
+            "precision": 0.041507,
+            "precision_weighted": 0.049813,
+            "recall": 0.070918,
+            "recall_weighted": 0.082474,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.14433,
+            "f1": 0.072694,
+            "f1_weighted": 0.093585,
+            "precision": 0.057785,
+            "precision_weighted": 0.077761,
+            "recall": 0.120635,
+            "recall_weighted": 0.14433,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.082369,
+        "f1": 0.042192,
+        "f1_weighted": 0.049403,
+        "precision": 0.034161,
+        "precision_weighted": 0.041359,
+        "recall": 0.075136,
+        "recall_weighted": 0.082369,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.082369,
+        "hf_subset": "es-ES",
+        "languages": [
+          "spa-Latn"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.132231,
+            "f1": 0.063891,
+            "f1_weighted": 0.078033,
+            "precision": 0.058201,
+            "precision_weighted": 0.07027,
+            "recall": 0.109831,
+            "recall_weighted": 0.132231,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.123967,
+            "f1": 0.070266,
+            "f1_weighted": 0.087423,
+            "precision": 0.06322,
+            "precision_weighted": 0.082255,
+            "recall": 0.107823,
+            "recall_weighted": 0.123967,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.041322,
+            "f1": 0.031306,
+            "f1_weighted": 0.024694,
+            "precision": 0.029553,
+            "precision_weighted": 0.023501,
+            "recall": 0.052721,
+            "recall_weighted": 0.041322,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.090909,
+            "f1": 0.047782,
+            "f1_weighted": 0.047368,
+            "precision": 0.036884,
+            "precision_weighted": 0.036651,
+            "recall": 0.093086,
+            "recall_weighted": 0.090909,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.1,
+            "f1": 0.066136,
+            "f1_weighted": 0.079724,
+            "precision": 0.059967,
+            "precision_weighted": 0.073007,
+            "recall": 0.084694,
+            "recall_weighted": 0.1,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.097686,
+        "f1": 0.055876,
+        "f1_weighted": 0.063448,
+        "precision": 0.049565,
+        "precision_weighted": 0.057137,
+        "recall": 0.089631,
+        "recall_weighted": 0.097686,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.097686,
+        "hf_subset": "pt-PT",
+        "languages": [
+          "por-Latn"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.04065,
+            "f1": 0.025309,
+            "f1_weighted": 0.031677,
+            "precision": 0.022386,
+            "precision_weighted": 0.028241,
+            "recall": 0.03382,
+            "recall_weighted": 0.04065,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.098361,
+            "f1": 0.068992,
+            "f1_weighted": 0.073187,
+            "precision": 0.069168,
+            "precision_weighted": 0.074248,
+            "recall": 0.098469,
+            "recall_weighted": 0.098361,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.081967,
+            "f1": 0.050377,
+            "f1_weighted": 0.06356,
+            "precision": 0.046974,
+            "precision_weighted": 0.06657,
+            "recall": 0.08706,
+            "recall_weighted": 0.081967,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.114754,
+            "f1": 0.052715,
+            "f1_weighted": 0.06395,
+            "precision": 0.062608,
+            "precision_weighted": 0.067939,
+            "recall": 0.086651,
+            "recall_weighted": 0.114754,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.098361,
+            "f1": 0.063504,
+            "f1_weighted": 0.075337,
+            "precision": 0.079648,
+            "precision_weighted": 0.101126,
+            "recall": 0.08869,
+            "recall_weighted": 0.098361,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.086819,
+        "f1": 0.052179,
+        "f1_weighted": 0.061542,
+        "precision": 0.056157,
+        "precision_weighted": 0.067625,
+        "recall": 0.078938,
+        "recall_weighted": 0.086819,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.086819,
+        "hf_subset": "de-DE",
+        "languages": [
+          "deu-Latn"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.068702,
+            "f1": 0.049784,
+            "f1_weighted": 0.051954,
+            "precision": 0.067793,
+            "precision_weighted": 0.066483,
+            "recall": 0.062825,
+            "recall_weighted": 0.068702,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.114504,
+            "f1": 0.064631,
+            "f1_weighted": 0.05218,
+            "precision": 0.047369,
+            "precision_weighted": 0.039462,
+            "recall": 0.154365,
+            "recall_weighted": 0.114504,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.030534,
+            "f1": 0.022343,
+            "f1_weighted": 0.026266,
+            "precision": 0.019913,
+            "precision_weighted": 0.023433,
+            "recall": 0.026026,
+            "recall_weighted": 0.030534,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.083969,
+            "f1": 0.065376,
+            "f1_weighted": 0.054219,
+            "precision": 0.059402,
+            "precision_weighted": 0.046931,
+            "recall": 0.099784,
+            "recall_weighted": 0.083969,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.053846,
+            "f1": 0.040368,
+            "f1_weighted": 0.040055,
+            "precision": 0.043517,
+            "precision_weighted": 0.044088,
+            "recall": 0.060714,
+            "recall_weighted": 0.053846,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.070311,
+        "f1": 0.0485,
+        "f1_weighted": 0.044935,
+        "precision": 0.047599,
+        "precision_weighted": 0.044079,
+        "recall": 0.080743,
+        "recall_weighted": 0.070311,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.070311,
+        "hf_subset": "nl-NL",
+        "languages": [
+          "nld-Latn"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.074074,
+            "f1": 0.03524,
+            "f1_weighted": 0.051747,
+            "precision": 0.037494,
+            "precision_weighted": 0.064805,
+            "recall": 0.071329,
+            "recall_weighted": 0.074074,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.111111,
+            "f1": 0.076837,
+            "f1_weighted": 0.083631,
+            "precision": 0.062912,
+            "precision_weighted": 0.070133,
+            "recall": 0.106411,
+            "recall_weighted": 0.111111,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.046296,
+            "f1": 0.042603,
+            "f1_weighted": 0.045122,
+            "precision": 0.060394,
+            "precision_weighted": 0.059681,
+            "recall": 0.046599,
+            "recall_weighted": 0.046296,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.055556,
+            "f1": 0.028493,
+            "f1_weighted": 0.027366,
+            "precision": 0.024501,
+            "precision_weighted": 0.023136,
+            "recall": 0.056122,
+            "recall_weighted": 0.055556,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.018692,
+            "f1": 0.006969,
+            "f1_weighted": 0.007294,
+            "precision": 0.004329,
+            "precision_weighted": 0.004531,
+            "recall": 0.017857,
+            "recall_weighted": 0.018692,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.061146,
+        "f1": 0.038028,
+        "f1_weighted": 0.043032,
+        "precision": 0.037926,
+        "precision_weighted": 0.044457,
+        "recall": 0.059664,
+        "recall_weighted": 0.061146,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.061146,
+        "hf_subset": "ru-RU",
+        "languages": [
+          "rus-Cyrl"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.097345,
+            "f1": 0.062784,
+            "f1_weighted": 0.059427,
+            "precision": 0.062259,
+            "precision_weighted": 0.064081,
+            "recall": 0.112925,
+            "recall_weighted": 0.097345,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.079646,
+            "f1": 0.052812,
+            "f1_weighted": 0.05273,
+            "precision": 0.039665,
+            "precision_weighted": 0.039642,
+            "recall": 0.079976,
+            "recall_weighted": 0.079646,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.044643,
+            "f1": 0.032824,
+            "f1_weighted": 0.039703,
+            "precision": 0.046127,
+            "precision_weighted": 0.066097,
+            "recall": 0.045683,
+            "recall_weighted": 0.044643,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.089286,
+            "f1": 0.059846,
+            "f1_weighted": 0.065879,
+            "precision": 0.05737,
+            "precision_weighted": 0.062877,
+            "recall": 0.079319,
+            "recall_weighted": 0.089286,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.089286,
+            "f1": 0.06277,
+            "f1_weighted": 0.068977,
+            "precision": 0.051741,
+            "precision_weighted": 0.05712,
+            "recall": 0.082212,
+            "recall_weighted": 0.089286,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.080041,
+        "f1": 0.054207,
+        "f1_weighted": 0.057343,
+        "precision": 0.051432,
+        "precision_weighted": 0.057963,
+        "recall": 0.080023,
+        "recall_weighted": 0.080041,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.080041,
+        "hf_subset": "pl-PL",
+        "languages": [
+          "pol-Latn"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.078261,
+            "f1": 0.048234,
+            "f1_weighted": 0.050373,
+            "precision": 0.051389,
+            "precision_weighted": 0.05285,
+            "recall": 0.077041,
+            "recall_weighted": 0.078261,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.104348,
+            "f1": 0.067404,
+            "f1_weighted": 0.074296,
+            "precision": 0.059924,
+            "precision_weighted": 0.067978,
+            "recall": 0.099948,
+            "recall_weighted": 0.104348,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.052174,
+            "f1": 0.037336,
+            "f1_weighted": 0.038125,
+            "precision": 0.031583,
+            "precision_weighted": 0.033159,
+            "recall": 0.052679,
+            "recall_weighted": 0.052174,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.052174,
+            "f1": 0.044796,
+            "f1_weighted": 0.040163,
+            "precision": 0.051281,
+            "precision_weighted": 0.050422,
+            "recall": 0.066752,
+            "recall_weighted": 0.052174,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.052632,
+            "f1": 0.047691,
+            "f1_weighted": 0.045685,
+            "precision": 0.046176,
+            "precision_weighted": 0.044812,
+            "recall": 0.055414,
+            "recall_weighted": 0.052632,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.067918,
+        "f1": 0.049092,
+        "f1_weighted": 0.049728,
+        "precision": 0.048071,
+        "precision_weighted": 0.049844,
+        "recall": 0.070367,
+        "recall_weighted": 0.067918,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.067918,
+        "hf_subset": "cs-CZ",
+        "languages": [
+          "ces-Latn"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.05042,
+            "f1": 0.036025,
+            "f1_weighted": 0.035531,
+            "precision": 0.033751,
+            "precision_weighted": 0.033141,
+            "recall": 0.05142,
+            "recall_weighted": 0.05042,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.092437,
+            "f1": 0.063185,
+            "f1_weighted": 0.070944,
+            "precision": 0.078082,
+            "precision_weighted": 0.088055,
+            "recall": 0.087302,
+            "recall_weighted": 0.092437,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.076271,
+            "f1": 0.0417,
+            "f1_weighted": 0.048937,
+            "precision": 0.043689,
+            "precision_weighted": 0.051022,
+            "recall": 0.066667,
+            "recall_weighted": 0.076271,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.059322,
+            "f1": 0.052992,
+            "f1_weighted": 0.056335,
+            "precision": 0.110402,
+            "precision_weighted": 0.148389,
+            "recall": 0.060937,
+            "recall_weighted": 0.059322,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.084746,
+            "f1": 0.044118,
+            "f1_weighted": 0.045036,
+            "precision": 0.037512,
+            "precision_weighted": 0.040142,
+            "recall": 0.091726,
+            "recall_weighted": 0.084746,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.072639,
+        "f1": 0.047604,
+        "f1_weighted": 0.051356,
+        "precision": 0.060687,
+        "precision_weighted": 0.07215,
+        "recall": 0.07161,
+        "recall_weighted": 0.072639,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.072639,
+        "hf_subset": "ko-KR",
+        "languages": [
+          "kor-Hang"
+        ]
+      },
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.108911,
+            "f1": 0.053973,
+            "f1_weighted": 0.065666,
+            "precision": 0.066752,
+            "precision_weighted": 0.078442,
+            "recall": 0.092687,
+            "recall_weighted": 0.108911,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.049505,
+            "f1": 0.03454,
+            "f1_weighted": 0.040711,
+            "precision": 0.041438,
+            "precision_weighted": 0.051663,
+            "recall": 0.041613,
+            "recall_weighted": 0.049505,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.03,
+            "f1": 0.011655,
+            "f1_weighted": 0.01366,
+            "precision": 0.007584,
+            "precision_weighted": 0.008911,
+            "recall": 0.025794,
+            "recall_weighted": 0.03,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.06,
+            "f1": 0.029389,
+            "f1_weighted": 0.027921,
+            "precision": 0.019345,
+            "precision_weighted": 0.01875,
+            "recall": 0.067659,
+            "recall_weighted": 0.06,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.07,
+            "f1": 0.052631,
+            "f1_weighted": 0.04927,
+            "precision": 0.052586,
+            "precision_weighted": 0.050783,
+            "recall": 0.083418,
+            "recall_weighted": 0.07,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.063683,
+        "f1": 0.036438,
+        "f1_weighted": 0.039445,
+        "precision": 0.037541,
+        "precision_weighted": 0.04171,
+        "recall": 0.062234,
+        "recall_weighted": 0.063683,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.063683,
+        "hf_subset": "zh-CN",
+        "languages": [
+          "zho-Hans"
+        ]
+      }
+    ]
+  },
+  "evaluation_time": 266.66408610343933,
+  "kg_co2_emissions": null,
+  "date": null
+}

maeb_voice_results/epoch_1/open_clap__CLAPNaFlex-base-ModernBERT/epoch_1/NMSQAPairClassification.json

@@ -0,0 +1,49 @@
+{
+  "dataset_revision": "d33eea302d8a64c0a2ee094cf39d77c0814fe87a",
+  "task_name": "NMSQAPairClassification",
+  "mteb_version": "2.10.9",
+  "scores": {
+    "test": [
+      {
+        "similarity_accuracy": 0.538012,
+        "similarity_f1": 0.661417,
+        "similarity_precision": 0.497041,
+        "similarity_recall": 0.988235,
+        "similarity_ap": 0.471475,
+        "cosine_accuracy": 0.538012,
+        "cosine_f1": 0.661417,
+        "cosine_precision": 0.497041,
+        "cosine_recall": 0.988235,
+        "cosine_ap": 0.471475,
+        "manhattan_accuracy": 0.54386,
+        "manhattan_f1": 0.666667,
+        "manhattan_precision": 0.5,
+        "manhattan_recall": 1.0,
+        "manhattan_ap": 0.471339,
+        "euclidean_accuracy": 0.54386,
+        "euclidean_f1": 0.666667,
+        "euclidean_precision": 0.5,
+        "euclidean_recall": 1.0,
+        "euclidean_ap": 0.471447,
+        "dot_accuracy": 0.538012,
+        "dot_f1": 0.661417,
+        "dot_precision": 0.497041,
+        "dot_recall": 0.988235,
+        "dot_ap": 0.475421,
+        "max_accuracy": 0.54386,
+        "max_f1": 0.666667,
+        "max_precision": 0.5,
+        "max_recall": 1.0,
+        "max_ap": 0.475421,
+        "main_score": 0.475421,
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ]
+      }
+    ]
+  },
+  "evaluation_time": 7.6367621421813965,
+  "kg_co2_emissions": null,
+  "date": null
+}

maeb_voice_results/epoch_1/open_clap__CLAPNaFlex-base-ModernBERT/epoch_1/RavdessZeroshot.json

@@ -0,0 +1,20 @@
+{
+  "dataset_revision": "9ab83d763c01b2dec59d79a6dcb44691d2fb80ee",
+  "task_name": "RavdessZeroshot",
+  "mteb_version": "2.10.9",
+  "scores": {
+    "train": [
+      {
+        "accuracy": 0.093056,
+        "main_score": 0.093056,
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ]
+      }
+    ]
+  },
+  "evaluation_time": 25.949893474578857,
+  "kg_co2_emissions": null,
+  "date": null
+}

maeb_voice_results/epoch_1/open_clap__CLAPNaFlex-base-ModernBERT/epoch_1/SpeechCommands.json

@@ -0,0 +1,140 @@
+{
+  "dataset_revision": "3ac713aa0829eeadda73182f38bbbd788d21254b",
+  "task_name": "SpeechCommands",
+  "mteb_version": "2.10.9",
+  "scores": {
+    "test": [
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.055215,
+            "f1": 0.015865,
+            "f1_weighted": 0.038045,
+            "precision": 0.017578,
+            "precision_weighted": 0.04748,
+            "recall": 0.040535,
+            "recall_weighted": 0.055215,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.033947,
+            "f1": 0.014055,
+            "f1_weighted": 0.037461,
+            "precision": 0.019043,
+            "precision_weighted": 0.05487,
+            "recall": 0.046959,
+            "recall_weighted": 0.033947,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.05726,
+            "f1": 0.010759,
+            "f1_weighted": 0.02861,
+            "precision": 0.014981,
+            "precision_weighted": 0.043085,
+            "recall": 0.030881,
+            "recall_weighted": 0.05726,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.007362,
+            "f1": 0.004035,
+            "f1_weighted": 0.00748,
+            "precision": 0.007888,
+            "precision_weighted": 0.020894,
+            "recall": 0.033028,
+            "recall_weighted": 0.007362,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.063395,
+            "f1": 0.015151,
+            "f1_weighted": 0.031465,
+            "precision": 0.015805,
+            "precision_weighted": 0.037268,
+            "recall": 0.038857,
+            "recall_weighted": 0.063395,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.031697,
+            "f1": 0.009353,
+            "f1_weighted": 0.020942,
+            "precision": 0.016224,
+            "precision_weighted": 0.045261,
+            "recall": 0.034004,
+            "recall_weighted": 0.031697,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.06319,
+            "f1": 0.010119,
+            "f1_weighted": 0.026334,
+            "precision": 0.019585,
+            "precision_weighted": 0.056494,
+            "recall": 0.036443,
+            "recall_weighted": 0.06319,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.018814,
+            "f1": 0.007712,
+            "f1_weighted": 0.018874,
+            "precision": 0.024177,
+            "precision_weighted": 0.070383,
+            "recall": 0.037351,
+            "recall_weighted": 0.018814,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.064417,
+            "f1": 0.018221,
+            "f1_weighted": 0.044105,
+            "precision": 0.020701,
+            "precision_weighted": 0.055651,
+            "recall": 0.044904,
+            "recall_weighted": 0.064417,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.008589,
+            "f1": 0.0042,
+            "f1_weighted": 0.009806,
+            "precision": 0.018932,
+            "precision_weighted": 0.056107,
+            "recall": 0.027103,
+            "recall_weighted": 0.008589,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.040389,
+        "f1": 0.010947,
+        "f1_weighted": 0.026312,
+        "precision": 0.017491,
+        "precision_weighted": 0.048749,
+        "recall": 0.037007,
+        "recall_weighted": 0.040389,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.040389,
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ]
+      }
+    ]
+  },
+  "evaluation_time": 139.20721983909607,
+  "kg_co2_emissions": null,
+  "date": null
+}

maeb_voice_results/epoch_1/open_clap__CLAPNaFlex-base-ModernBERT/epoch_1/SpokenSQuADT2ARetrieval.json

@@ -0,0 +1,167 @@
+{
+  "dataset_revision": "b311394fa5ab5e003012304799d0d724d64303b3",
+  "task_name": "SpokenSQuADT2ARetrieval",
+  "mteb_version": "2.10.9",
+  "scores": {
+    "test": [
+      {
+        "ndcg_at_1": 0.0,
+        "ndcg_at_3": 0.0,
+        "ndcg_at_5": 0.0,
+        "ndcg_at_10": 0.006,
+        "ndcg_at_20": 0.0197,
+        "ndcg_at_100": 0.06909,
+        "ndcg_at_1000": 0.15582,
+        "map_at_1": 0.0,
+        "map_at_3": 0.0,
+        "map_at_5": 0.0,
+        "map_at_10": 0.0022,
+        "map_at_20": 0.00607,
+        "map_at_100": 0.01154,
+        "map_at_1000": 0.01543,
+        "recall_at_1": 0.0,
+        "recall_at_3": 0.0,
+        "recall_at_5": 0.0,
+        "recall_at_10": 0.02,
+        "recall_at_20": 0.07333,
+        "recall_at_100": 0.35833,
+        "recall_at_1000": 1.0,
+        "accuracy": 0.0,
+        "precision_at_1": 0.0,
+        "precision_at_3": 0.0,
+        "precision_at_5": 0.0,
+        "precision_at_10": 0.002,
+        "precision_at_20": 0.00367,
+        "precision_at_100": 0.00363,
+        "precision_at_1000": 0.00102,
+        "mrr_at_1": 0.0,
+        "mrr_at_3": 0.0,
+        "mrr_at_5": 0.0,
+        "mrr_at_10": 0.002204,
+        "mrr_at_20": 0.006073,
+        "mrr_at_100": 0.011624,
+        "mrr_at_1000": 0.015444,
+        "nauc_ndcg_at_1_max": NaN,
+        "nauc_ndcg_at_1_std": NaN,
+        "nauc_ndcg_at_1_diff1": NaN,
+        "nauc_ndcg_at_3_max": NaN,
+        "nauc_ndcg_at_3_std": NaN,
+        "nauc_ndcg_at_3_diff1": NaN,
+        "nauc_ndcg_at_5_max": NaN,
+        "nauc_ndcg_at_5_std": NaN,
+        "nauc_ndcg_at_5_diff1": NaN,
+        "nauc_ndcg_at_10_max": 0.08549,
+        "nauc_ndcg_at_10_std": 0.083573,
+        "nauc_ndcg_at_10_diff1": -0.064105,
+        "nauc_ndcg_at_20_max": -0.081306,
+        "nauc_ndcg_at_20_std": -0.153093,
+        "nauc_ndcg_at_20_diff1": -0.222134,
+        "nauc_ndcg_at_100_max": -0.002663,
+        "nauc_ndcg_at_100_std": -0.019355,
+        "nauc_ndcg_at_100_diff1": -0.023636,
+        "nauc_ndcg_at_1000_max": -0.021725,
+        "nauc_ndcg_at_1000_std": -0.096188,
+        "nauc_ndcg_at_1000_diff1": -0.11645,
+        "nauc_map_at_1_max": NaN,
+        "nauc_map_at_1_std": NaN,
+        "nauc_map_at_1_diff1": NaN,
+        "nauc_map_at_3_max": NaN,
+        "nauc_map_at_3_std": NaN,
+        "nauc_map_at_3_diff1": NaN,
+        "nauc_map_at_5_max": NaN,
+        "nauc_map_at_5_std": NaN,
+        "nauc_map_at_5_diff1": NaN,
+        "nauc_map_at_10_max": 0.122425,
+        "nauc_map_at_10_std": 0.101596,
+        "nauc_map_at_10_diff1": -0.034639,
+        "nauc_map_at_20_max": -0.065711,
+        "nauc_map_at_20_std": -0.119788,
+        "nauc_map_at_20_diff1": -0.207921,
+        "nauc_map_at_100_max": -0.004923,
+        "nauc_map_at_100_std": -0.065245,
+        "nauc_map_at_100_diff1": -0.095534,
+        "nauc_map_at_1000_max": -0.015797,
+        "nauc_map_at_1000_std": -0.088721,
+        "nauc_map_at_1000_diff1": -0.126155,
+        "nauc_recall_at_1_max": NaN,
+        "nauc_recall_at_1_std": NaN,
+        "nauc_recall_at_1_diff1": NaN,
+        "nauc_recall_at_3_max": NaN,
+        "nauc_recall_at_3_std": NaN,
+        "nauc_recall_at_3_diff1": NaN,
+        "nauc_recall_at_5_max": NaN,
+        "nauc_recall_at_5_std": NaN,
+        "nauc_recall_at_5_diff1": NaN,
+        "nauc_recall_at_10_max": 0.062204,
+        "nauc_recall_at_10_std": 0.072176,
+        "nauc_recall_at_10_diff1": -0.082685,
+        "nauc_recall_at_20_max": -0.087738,
+        "nauc_recall_at_20_std": -0.171171,
+        "nauc_recall_at_20_diff1": -0.228175,
+        "nauc_recall_at_100_max": -0.001843,
+        "nauc_recall_at_100_std": 0.009175,
+        "nauc_recall_at_100_diff1": 0.014051,
+        "nauc_recall_at_1000_max": NaN,
+        "nauc_recall_at_1000_std": NaN,
+        "nauc_recall_at_1000_diff1": NaN,
+        "nauc_precision_at_1_max": NaN,
+        "nauc_precision_at_1_std": NaN,
+        "nauc_precision_at_1_diff1": NaN,
+        "nauc_precision_at_3_max": NaN,
+        "nauc_precision_at_3_std": NaN,
+        "nauc_precision_at_3_diff1": NaN,
+        "nauc_precision_at_5_max": NaN,
+        "nauc_precision_at_5_std": NaN,
+        "nauc_precision_at_5_diff1": NaN,
+        "nauc_precision_at_10_max": 0.062204,
+        "nauc_precision_at_10_std": 0.072176,
+        "nauc_precision_at_10_diff1": -0.082685,
+        "nauc_precision_at_20_max": -0.087738,
+        "nauc_precision_at_20_std": -0.171171,
+        "nauc_precision_at_20_diff1": -0.228175,
+        "nauc_precision_at_100_max": -0.008306,
+        "nauc_precision_at_100_std": 0.002227,
+        "nauc_precision_at_100_diff1": 0.00755,
+        "nauc_precision_at_1000_max": 0.054506,
+        "nauc_precision_at_1000_std": -0.178121,
+        "nauc_precision_at_1000_diff1": -0.064893,
+        "nauc_mrr_at_1_max": NaN,
+        "nauc_mrr_at_1_std": NaN,
+        "nauc_mrr_at_1_diff1": NaN,
+        "nauc_mrr_at_3_max": NaN,
+        "nauc_mrr_at_3_std": NaN,
+        "nauc_mrr_at_3_diff1": NaN,
+        "nauc_mrr_at_5_max": NaN,
+        "nauc_mrr_at_5_std": NaN,
+        "nauc_mrr_at_5_diff1": NaN,
+        "nauc_mrr_at_10_max": 0.122425,
+        "nauc_mrr_at_10_std": 0.101596,
+        "nauc_mrr_at_10_diff1": -0.034639,
+        "nauc_mrr_at_20_max": -0.065711,
+        "nauc_mrr_at_20_std": -0.119788,
+        "nauc_mrr_at_20_diff1": -0.207921,
+        "nauc_mrr_at_100_max": -0.007702,
+        "nauc_mrr_at_100_std": -0.067465,
+        "nauc_mrr_at_100_diff1": -0.097505,
+        "nauc_mrr_at_1000_max": -0.017331,
+        "nauc_mrr_at_1000_std": -0.089407,
+        "nauc_mrr_at_1000_diff1": -0.126329,
+        "hit_rate_at_1": 0.0,
+        "hit_rate_at_3": 0.0,
+        "hit_rate_at_5": 0.0,
+        "hit_rate_at_10": 0.02,
+        "hit_rate_at_20": 0.07333,
+        "hit_rate_at_100": 0.36333,
+        "hit_rate_at_1000": 1.0,
+        "main_score": 0.0,
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn"
+        ]
+      }
+    ]
+  },
+  "evaluation_time": 5.027910470962524,
+  "kg_co2_emissions": null,
+  "date": null
+}

maeb_voice_results/epoch_1/open_clap__CLAPNaFlex-base-ModernBERT/epoch_1/VoxPopuliLanguageID.json

@@ -0,0 +1,89 @@
+{
+  "dataset_revision": "d5fb9661054ba250e2c03adeb9a702ad55e73f27",
+  "task_name": "VoxPopuliLanguageID",
+  "mteb_version": "2.10.9",
+  "scores": {
+    "train": [
+      {
+        "scores_per_experiment": [
+          {
+            "accuracy": 0.18,
+            "f1": 0.168587,
+            "f1_weighted": 0.152911,
+            "precision": 0.157609,
+            "precision_weighted": 0.150462,
+            "recall": 0.214762,
+            "recall_weighted": 0.18,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.23,
+            "f1": 0.222817,
+            "f1_weighted": 0.227966,
+            "precision": 0.306803,
+            "precision_weighted": 0.302478,
+            "recall": 0.223153,
+            "recall_weighted": 0.23,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.13,
+            "f1": 0.126111,
+            "f1_weighted": 0.141514,
+            "precision": 0.165769,
+            "precision_weighted": 0.189712,
+            "recall": 0.119048,
+            "recall_weighted": 0.13,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.2,
+            "f1": 0.184493,
+            "f1_weighted": 0.181425,
+            "precision": 0.25,
+            "precision_weighted": 0.25,
+            "recall": 0.205934,
+            "recall_weighted": 0.2,
+            "ap": null,
+            "ap_weighted": null
+          },
+          {
+            "accuracy": 0.16,
+            "f1": 0.131028,
+            "f1_weighted": 0.124762,
+            "precision": 0.113152,
+            "precision_weighted": 0.108427,
+            "recall": 0.168922,
+            "recall_weighted": 0.16,
+            "ap": null,
+            "ap_weighted": null
+          }
+        ],
+        "accuracy": 0.18,
+        "f1": 0.166607,
+        "f1_weighted": 0.165716,
+        "precision": 0.198666,
+        "precision_weighted": 0.200216,
+        "recall": 0.186364,
+        "recall_weighted": 0.18,
+        "ap": NaN,
+        "ap_weighted": NaN,
+        "main_score": 0.18,
+        "hf_subset": "default",
+        "languages": [
+          "eng-Latn",
+          "fra-Latn",
+          "spa-Latn",
+          "pol-Latn",
+          "deu-Latn"
+        ]
+      }
+    ]
+  },
+  "evaluation_time": 9.424651861190796,
+  "kg_co2_emissions": null,
+  "date": null
+}

maeb_voice_results/epoch_1/open_clap__CLAPNaFlex-base-ModernBERT/epoch_1/model_meta.json

@@ -0,0 +1 @@
+{"loader_kwargs": {}, "name": "open_clap/CLAPNaFlex-base-ModernBERT", "revision": "epoch_1", "release_date": null, "languages": ["eng-Latn"], "n_parameters": null, "n_active_parameters_override": null, "n_embedding_parameters": null, "memory_usage_mb": null, "max_tokens": Infinity, "embed_dim": null, "license": null, "open_weights": true, "public_training_code": null, "public_training_data": null, "framework": ["PyTorch"], "reference": null, "similarity_fn_name": "cosine", "use_instructions": false, "training_datasets": null, "adapted_from": null, "superseded_by": null, "modalities": ["audio", "text"], "model_type": ["dense"], "citation": null, "contacts": null, "experiment_kwargs": null, "loader": null, "is_cross_encoder": false}

params.txt

@@ -0,0 +1,124 @@
+accum_freq: 1
+audio_ext: flac
+aug_cfg: {}
+batch_size: 64
+beta1: 0.9
+beta2: 0.95
+cache_dir: None
+caption_weight: 0.0
+checkpoint_path: smoke_A_baseline/checkpoints
+classification_label_key: labels
+classification_num_classes: 527
+classification_weight: 0.0
+coca_caption_loss_weight: 2.0
+coca_contrastive_loss_weight: 1.0
+compile_mode: default
+contrastive_weight: 1.0
+copy_codebase: False
+csv_caption_key: title
+csv_img_key: filepath
+csv_separator: 	
+dac_model_type: 44khz
+dac_num_codebooks: 1
+dac_tokenize: False
+data_filling: pad
+data_truncating: rand_trunc
+dataset_resampled: True
+dataset_type: webdataset-audio
+ddp_static_graph: True
+debug: False
+delete_previous_checkpoint: False
+device: cuda:0
+dist_backend: None
+dist_url: None
+distill: False
+distill_model: None
+distill_pretrained: None
+distributed: True
+enable_fusion: False
+epochs: 1
+epochs_cooldown: None
+eps: 1e-08
+force_context_length: None
+force_custom_text: False
+force_image_size: None
+force_patch_dropout: None
+force_quick_gelu: False
+fsdp2: False
+gather_with_grad: True
+grad_checkpointing: False
+grad_clip_norm: 1.0
+horovod: False
+image_interpolation: None
+image_mean: None
+image_resize_mode: None
+image_std: None
+imagenet_v2: None
+imagenet_val: None
+int16_normalize: False
+local_loss: True
+local_rank: 0
+lock_audio: False
+lock_image: False
+lock_image_freeze_bn_stats: False
+lock_image_unlocked_groups: 0
+lock_text: False
+lock_text_freeze_layer_norm: False
+lock_text_unlocked_layers: 0
+log_every_n_steps: 100
+log_level: 20
+log_local: False
+log_path: smoke_A_baseline/out.log
+log_step_timings: False
+logs: voiceclap/checkpoints
+loss_dist_impl: None
+lr: 0.0003
+lr_cooldown_end: 0.0
+lr_cooldown_power: 1.0
+lr_scheduler: cosine
+model: CLAPNaFlex-base-ModernBERT
+momentum: None
+naflex: True
+name: smoke_A_baseline
+no_set_device_rank: False
+opt: adamw
+pack_max_clips: 4
+precision: amp_bfloat16
+pretrained: 
+pretrained_audio: naflexvit_base_patch16_siglip.v2_webli
+pretrained_image: False
+rank: 0
+remote_sync: None
+remote_sync_frequency: 300
+remote_sync_protocol: s3
+report_to: tensorboard
+resume: None
+save_frequency: 1
+save_most_recent: True
+seed: 0
+sequence_packing: False
+siglip: True
+skip_scheduler: False
+synthetic_seq_len: 0
+tensorboard: True
+tensorboard_path: smoke_A_baseline/tensorboard
+torchcompile: False
+torchscript: False
+trace: False
+train_data: laions_got_talent_clean_with_captions/000000.tar::emolia-balanced-5M-subset-flac48k-wds/emolia-000000.tar::majestrino-data/000000.tar::synthetic_vocal_bursts/000000.tar::ears/000000.tar::improved_synthetic_vocal_burts/000000.tar
+train_data_file: None
+train_data_upsampling_factors: None
+train_num_samples: 256000
+use_bn_sync: False
+use_bnb_linear: None
+val_data: None
+val_frequency: 1
+val_num_samples: None
+wandb: False
+wandb_notes: 
+wandb_project_name: open-clip
+warmup: 100
+wd: 0.2
+workers: 12
+world_size: 4
+zeroshot_frequency: 1