Upload folder using huggingface_hub

config.json

@@ -0,0 +1,111 @@
+{
+  "_name_or_path": "microsoft/unispeech-sat-base-plus-sd",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "UniSpeechSatForAudioFrameClassification"
+  ],
+  "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": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "speaker_0",
+    "1": "speaker_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "speaker_0": 0,
+    "speaker_1": 1
+  },
+  "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": "unispeech-sat",
+  "num_attention_heads": 12,
+  "num_clusters": 504,
+  "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,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "transformers_version": "4.33.2",
+  "use_weighted_layer_sum": true,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da7fd6d576fd3148dca442265adc4985aec50a4dcb5994205087c4f1ddb507a
+size 377820930

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda8f086addbf9ae06b0052b03cb18f055d5eaf9714f9bf32fbf2d704f010f9c
+size 95301468

preprocessor_config.json

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

quantize_config.json

@@ -0,0 +1,32 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Div",
+                "ReduceSum",
+                "Shape",
+                "Transpose",
+                "Concat",
+                "Gather",
+                "Sub",
+                "MatMul",
+                "Pow",
+                "Slice",
+                "Unsqueeze",
+                "Conv",
+                "Erf",
+                "InstanceNormalization",
+                "Constant",
+                "ReduceMean",
+                "Reshape",
+                "Softmax",
+                "Sqrt",
+                "Mul",
+                "Add"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}