add model

config.json

@@ -0,0 +1,43 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "Speech2TextForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "conv_channels": 32,
+  "conv_kernel_sizes": [
+    5,
+    5
+  ],
+  "d_model": 16,
+  "decoder_attention_heads": 4,
+  "decoder_ffn_dim": 4,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 2,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 4,
+  "encoder_ffn_dim": 4,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 2,
+  "eos_token_id": 2,
+  "init_std": 0.02,
+  "input_channels": 1,
+  "input_feat_per_channel": 24,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 20,
+  "max_source_positions": 20,
+  "max_target_positions": 20,
+  "model_type": "speech_to_text",
+  "num_conv_layers": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.2",
+  "use_cache": true,
+  "vocab_size": 10000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 5,
+  "max_new_tokens": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.52.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7261459bb4f43dfb595e3e576cef19b8ea2a095e29ed8837236014cd56865016
+size 705880

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "dither": 0.0,
+  "do_ceptral_normalize": true,
+  "feature_extractor_type": "Speech2TextFeatureExtractor",
+  "feature_size": 24,
+  "normalize_means": true,
+  "normalize_vars": true,
+  "num_mel_bins": 24,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052a168787a9160b4b2ba54e4995e9600298812c34191ca3f70cea51cd4f5c1e
+size 416684

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": true,
+  "do_upper_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "lang_codes": null,
+  "model_max_length": 20,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tgt_lang": null,
+  "tokenizer_class": "Speech2TextTokenizer",
+  "unk_token": "<unk>"
+}