Upload folder using huggingface_hub

wav2vec2-large-emotion-detection-german.config

@@ -0,0 +1,131 @@
+Wav2Vec2Config {
+  "_name_or_path": "padmalcom/wav2vec2-large-emotion-detection-german",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSpeechClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "finetuning_task": "wav2vec2_clf",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "anger",
+    "1": "boredom",
+    "2": "disgust",
+    "3": "fear",
+    "4": "happiness",
+    "5": "sadness",
+    "6": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "anger": 0,
+    "boredom": 1,
+    "disgust": 2,
+    "fear": 3,
+    "happiness": 4,
+    "neutral": 6,
+    "sadness": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "pooling_mode": "mean",
+  "problem_type": "single_label_classification",
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

wav2vec2-large-emotion-detection-german.feature

@@ -0,0 +1,9 @@
+Wav2Vec2FeatureExtractor {
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

wav2vec2-large-emotion-detection-german.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ccb3dce44226c65ae9a961595944a833fb3b027d6cfe5f2865f00e77faeda4d
+size 1263408034

wav2vec2-large-emotion-detection-german.processor

@@ -0,0 +1,21 @@
+Wav2Vec2Processor:
+- feature_extractor: Wav2Vec2FeatureExtractor {
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}
+
+- tokenizer: Wav2Vec2CTCTokenizer(name_or_path='padmalcom/wav2vec2-large-emotion-detection-german', vocab_size=32, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>', 'pad_token': '<pad>'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={
+	0: AddedToken("<pad>", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+	1: AddedToken("<s>", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+	2: AddedToken("</s>", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+	3: AddedToken("<unk>", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+}
+
+{
+  "processor_class": "Wav2Vec2Processor"
+}

wav2vec2-large-emotion-detection-german.tokens

@@ -0,0 +1,32 @@
+0: <pad>
+1: <s>
+2: </s>
+3: <unk>
+4: '|'
+5: E
+6: T
+7: A
+8: O
+9: N
+10: I
+11: H
+12: S
+13: R
+14: D
+15: L
+16: U
+17: M
+18: W
+19: C
+20: F
+21: G
+22: Y
+23: P
+24: B
+25: V
+26: K
+27: ''''
+28: X
+29: J
+30: Q
+31: Z

wav2vec2-large-emotion-detection-german.yaml

@@ -0,0 +1,14 @@
+feature_extractor: Wav2Vec2FeatureExtractor
+labels:
+  0: anger
+  1: boredom
+  2: disgust
+  3: fear
+  4: happiness
+  5: sadness
+  6: neutral
+model: Wav2Vec2ForSequenceClassification
+sampling_rate: 16000
+shape:
+- 1
+- 320000