Adding ONNX file of this model

README.md

@@ -12,8 +12,13 @@ tags:
 - armenian
 - compact-model
 - generated_from_trainer
+- onnx
 datasets:
 - Chillarmo/common_voice_20_armenian
+license: mit
+metrics:
+- wer
+pipeline_tag: automatic-speech-recognition
 model-index:
 - name: ATOM (Armenian Tiny Optimized Model)
   results:
@@ -32,10 +37,6 @@ model-index:
     - type: exact_match
       value: 10.06
       name: Exact Match
-license: mit
-metrics:
-- wer
-pipeline_tag: automatic-speech-recognition
 ---
 
 # ATOM: Armenian Tiny Optimized Model

onnx/config.json

@@ -0,0 +1,49 @@
+{
+  "_attn_implementation_autoset": true,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1024,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 2,
+  "decoder_start_token_id": 1,
+  "dropout": 0.0,
+  "dtype": "float16",
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 2,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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,
+  "max_length": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 0,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 5000
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca32bce955613ecc749d3069d7defc2a57185b57ceeb52d0b72fbd5b47edd90b
+size 31903743

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06f0c0c87c402cc15586542239981e3345f711ab3a6ad5066e617b6049b5822
+size 31974461

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95fcf0ed8eabf2d95e3a01245f646fc5623f1f3c766b790c188b687d72aea765
+size 29535463

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300bfe68ebfd4e03ed4defc074b026c4c96a3ab9ce83a740f2e908725342c674
+size 32888634

onnx/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "begin_suppress_tokens": [],
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 448,
+  "pad_token_id": 0,
+  "suppress_tokens": [],
+  "transformers_version": "4.51.3",
+  "vocab_size": 5000
+}

onnx/preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

onnx/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

onnx/tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 448,
+  "pad_token": "<pad>",
+  "processor_class": "WhisperProcessor",
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": "<unk>"
+}