Initial model upload with model card

README.md

@@ -0,0 +1,41 @@
+---
+license: apache-2.0
+datasets:
+- stapesai/ssi-speech-emotion-recognition
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+pipeline_tag: audio-classification
+---
+
+# Multimodal Emotion Speech Recognition
+
+## Model Description
+This model performs emotion recognition from speech using a multimodal approach, utilizing:
+- **Audio Model**: Wav2Vec2 Base
+## Dataset
+- **Dataset Name**: [stapesai/ssi-speech-emotion-recognition](https://huggingface.co/datasets/stapesai/ssi-speech-emotion-recognition)
+
+## Evaluation Results
+
+### Classification Report
+```
+              precision    recall  f1-score   support
+
+         ANG       0.97      0.93      0.95        30
+         CAL       0.00      0.00      0.00         0
+         DIS       0.95      0.90      0.92        20
+         FEA       0.76      0.70      0.73        27
+         HAP       0.87      0.82      0.84        33
+         NEU       0.96      0.96      0.96        25
+         SAD       0.73      1.00      0.84        19
+         SUR       0.88      0.78      0.82         9
+
+    accuracy                           0.87       163
+   macro avg       0.76      0.76      0.76       163
+weighted avg       0.88      0.87      0.87       163
+```
+
+**Overall Accuracy**: 87%

labels.json

@@ -0,0 +1,10 @@
+{
+  "ANG": 0,
+  "CAL": 1,
+  "DIS": 2,
+  "FEA": 3,
+  "HAP": 4,
+  "NEU": 5,
+  "SAD": 6,
+  "SUR": 7
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13e4708ab39d7bdf3ab82df2614a5d4091859a830a23f0910313c1abc64b651
+size 379152343

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/events.out.tfevents.1768038394.MSI.3568.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277d98c3d65e4b5b89bbcc2a89cb01d975ef4e458ca8aeaf360960bd99bda193
+size 42683

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

test_results.txt

@@ -0,0 +1,14 @@
+              precision    recall  f1-score   support
+
+         ANG       0.97      0.93      0.95        30
+         CAL       0.00      0.00      0.00         0
+         DIS       0.95      0.90      0.92        20
+         FEA       0.76      0.70      0.73        27
+         HAP       0.87      0.82      0.84        33
+         NEU       0.96      0.96      0.96        25
+         SAD       0.73      1.00      0.84        19
+         SUR       0.88      0.78      0.82         9
+
+    accuracy                           0.87       163
+   macro avg       0.76      0.76      0.76       163
+weighted avg       0.88      0.87      0.87       163

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "do_normalize": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "return_attention_mask": false,
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,34 @@
+{
+  "'": 27,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "A": 7,
+  "B": 24,
+  "C": 19,
+  "D": 14,
+  "E": 5,
+  "F": 20,
+  "G": 21,
+  "H": 11,
+  "I": 10,
+  "J": 29,
+  "K": 26,
+  "L": 15,
+  "M": 17,
+  "N": 9,
+  "O": 8,
+  "P": 23,
+  "Q": 30,
+  "R": 13,
+  "S": 12,
+  "T": 6,
+  "U": 16,
+  "V": 25,
+  "W": 18,
+  "X": 28,
+  "Y": 22,
+  "Z": 31,
+  "|": 4
+}