Upload model

config.json

@@ -0,0 +1,141 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "change language",
+    "1": "activate",
+    "2": "deactivate",
+    "3": "increase",
+    "4": "decrease",
+    "5": "bring",
+    "6": "none_object",
+    "7": "music",
+    "8": "lights",
+    "9": "volume",
+    "10": "heat",
+    "11": "lamp",
+    "12": "newspaper",
+    "13": "juice",
+    "14": "socks",
+    "15": "Chinese",
+    "16": "Korean",
+    "17": "English",
+    "18": "German",
+    "19": "shoes",
+    "20": "none_location",
+    "21": "kitchen",
+    "22": "bedroom",
+    "23": "washroom"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Chinese": 15,
+    "English": 17,
+    "German": 18,
+    "Korean": 16,
+    "activate": 1,
+    "bedroom": 22,
+    "bring": 5,
+    "change language": 0,
+    "deactivate": 2,
+    "decrease": 4,
+    "heat": 10,
+    "increase": 3,
+    "juice": 13,
+    "kitchen": 21,
+    "lamp": 11,
+    "lights": 8,
+    "music": 7,
+    "newspaper": 12,
+    "none_location": 20,
+    "none_object": 6,
+    "shoes": 19,
+    "socks": 14,
+    "volume": 9,
+    "washroom": 23
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0.dev0",
+  "use_weighted_layer_sum": true,
+  "vocab_size": 32
+}

preprocessor_config.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1a902a3e157baabcc01424c49cf3958e41031139a88dd752a35bfbfc538242
+size 378381649