Update tiny models for VoxtralRealtimeEncoder

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,26 @@
+{
+  "activation_function": "silu",
+  "architectures": [
+    "VoxtralRealtimeEncoder"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "head_dim": 8,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 256,
+  "model_type": "voxtral_realtime_encoder",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_mel_bins": 80,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 750,
+  "transformers_version": "5.16.0.dev0",
+  "vocab_size": 99
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b25cb988f3f9cb27f92ec7cfd7865d96d2e131a39b46e26913151f8aed5314
+size 88496

preprocessor_config.json

@@ -0,0 +1,12 @@
+{
+  "feature_extractor_type": "VoxtralRealtimeFeatureExtractor",
+  "feature_size": 128,
+  "global_log_mel_max": 1.5,
+  "hop_length": 160,
+  "n_fft": 400,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_length": 400
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8434af1d39eba99f0ef46cf1450bf1a63fa941a26933a1ef5dbbf4adf0d00e44
+size 14910348