trfs integration

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "ParakeetForCTC"
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "dtype": "bfloat16",
+  "encoder_config": {
+    "activation_dropout": 0.1,
+    "attention_bias": true,
+    "attention_dropout": 0.1,
+    "conv_kernel_size": 9,
+    "dropout": 0.1,
+    "dropout_positions": 0.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layerdrop": 0.1,
+    "max_position_embeddings": 5000,
+    "model_type": "parakeet_encoder",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 8,
+    "num_mel_bins": 80,
+    "scale_input": true,
+    "subsampling_conv_channels": 256,
+    "subsampling_conv_kernel_size": 3,
+    "subsampling_conv_stride": 2,
+    "subsampling_factor": 8
+  },
+  "initializer_range": 0.02,
+  "model_type": "parakeet_ctc",
+  "pad_token_id": 1024,
+  "transformers_version": "4.57.0.dev0",
+  "vocab_size": 1025
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f5b1d2bc66d4a812a1c8ea48a9aa8678f863e1bd3ecbec3c75abd720897fda
+size 2435506188

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "feature_extractor_type": "ParakeetFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 512,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "preemphasis": 0.97,
+  "processor_class": "ParakeetProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_length": 400
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1024": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "ParakeetProcessor",
+  "tokenizer_class": "ParakeetTokenizerFast",
+  "unk_token": "<unk>"
+}