Initial Commit

app.py

@@ -0,0 +1,28 @@
+import gradio as gr
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from torch.nn.functional import softmax
+
+
+class TextEmotionDetector:
+    def __init__(self, model_path):
+        self.model = AutoModelForSequenceClassification.from_pretrained(model_path)
+        self.tokenizer = AutoTokenizer.from_pretrained(model_path)
+        self.label_key = {0: 'surprise', 1: 'anger', 2: 'love', 3: 'joy', 4: 'fear', 5: 'sadness'}
+    
+    def inference(self, text):
+        embedding = self.tokenizer(text, return_tensors="pt")
+        logits = self.model(input_ids=embedding['input_ids'], attention_mask=embedding['attention_mask'], 
+                      token_type_ids=embedding['token_type_ids'])['logits']
+
+        probabilities = softmax(logits)
+        predication = { self.label_key[i]: float(prob) for i, prob in enumerate(probabilities[0]) }
+
+        return predication
+        
+detector = TextEmotionDetector("emotion-nlp-model")
+
+text = gr.inputs.Textbox(lines=1, placeholder="Please enter text")
+label = gr.outputs.Label()
+interface = gr.Interface(fn=detector.inference, inputs=text, outputs=label, title="Text Emotion Classifier")
+
+interface.launch(inline=False)

emotion-nlp-model/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

emotion-nlp-model/config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

emotion-nlp-model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb7f817c92bba709bb086fc30a5ecd7763b2919a47b6af383e979452bfa9a21
+size 567637241

emotion-nlp-model/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

emotion-nlp-model/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

emotion-nlp-model/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "microsoft/deberta-v3-small",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

emotion-nlp-model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb46604b1d3ded3d4fd466034994c74113d9910bf996689d5096139ca71847c
+size 3451

requirements.txt

@@ -0,0 +1,2 @@
+torch==1.13.1
+transformers==4.26.0