Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-small",
+  "_name_or_path": "ihanif/whisper-test",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -53,8 +53,7 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.45.1",
+  "transformers_version": "4.33.2",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -250,5 +250,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.45.1"
+  "transformers_version": "4.33.2"
 }

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9dea2ab4df6f44eaf13d1290361380f9f49266e7ea9433e7875c4b368fb4111
+size 614830372

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217f8b7a5d931f9b09572f876a5e08d05bfb6be5952f740f1c387fb0c12f08c7
+size 615265438

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248d45be5696943e3008fef1931d9e4f764483bf5b09f3056155fcf980eb560e
+size 156599474

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c0b607829e4e829908ffa2422334b3511550b78f12600e0ac1affc828ebe03
+size 155906420

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d1b835dcc5b15bc86f46581cb51aa2158639b84f94de52f5f16b0d2a8c628f
+size 558093683

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f0008775a9863bc6ca2e705473c6bb1fc69c8b9f0e677585f7a4ad8a1729989
+size 141586018

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf6b994039cb8c3438013ee45dcdc5a8e1c4e3c1b7937e17cb30e442eb59f8d
+size 352812844

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9050e7bd292739561587e286b861ec49ee29b18c59a4d60e255d1089da1dcb
+size 92289694

quantize_config.json

@@ -0,0 +1,115 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_model": {
+            "op_types": [
+                "Squeeze",
+                "Reshape",
+                "Transpose",
+                "Unsqueeze",
+                "Softmax",
+                "Less",
+                "Expand",
+                "Equal",
+                "Shape",
+                "Sub",
+                "Pow",
+                "Constant",
+                "Sqrt",
+                "ConstantOfShape",
+                "Slice",
+                "Mul",
+                "ReduceMean",
+                "Div",
+                "Concat",
+                "Where",
+                "Cast",
+                "Erf",
+                "Gather",
+                "Add",
+                "MatMul",
+                "Range"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Squeeze",
+                "Reshape",
+                "Transpose",
+                "If",
+                "Unsqueeze",
+                "Softmax",
+                "Less",
+                "Expand",
+                "Equal",
+                "Shape",
+                "Sub",
+                "Pow",
+                "Constant",
+                "Sqrt",
+                "ConstantOfShape",
+                "Slice",
+                "Mul",
+                "ReduceMean",
+                "Div",
+                "Concat",
+                "Where",
+                "Cast",
+                "Erf",
+                "Gather",
+                "Add",
+                "MatMul",
+                "Range"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_with_past_model": {
+            "op_types": [
+                "Unsqueeze",
+                "Softmax",
+                "Slice",
+                "Reshape",
+                "Mul",
+                "Transpose",
+                "ReduceMean",
+                "Div",
+                "Erf",
+                "Gather",
+                "Add",
+                "Shape",
+                "Sub",
+                "Concat",
+                "Pow",
+                "Constant",
+                "Sqrt",
+                "MatMul"
+            ],
+            "weight_type": "QInt8"
+        },
+        "encoder_model": {
+            "op_types": [
+                "Unsqueeze",
+                "Concat",
+                "Softmax",
+                "Reshape",
+                "Mul",
+                "Transpose",
+                "Conv",
+                "ReduceMean",
+                "Div",
+                "Erf",
+                "Gather",
+                "Add",
+                "Sub",
+                "Shape",
+                "MatMul",
+                "Pow",
+                "Constant",
+                "Sqrt"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

tokenizer_config.json

@@ -12976,14 +12976,43 @@
     "<|nocaptions|>",
     "<|notimestamps|>"
   ],
-  "bos_token": "<|endoftext|>",
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "errors": "replace",
   "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "processor_class": "WhisperProcessor",
   "return_attention_mask": false,
   "tokenizer_class": "WhisperTokenizer",
-  "unk_token": "<|endoftext|>"
+  "trust_remote_code": false,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }