Update tiny models for VoxtralEncoder

.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 +1,22 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "VoxtralEncoder"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "layerdrop": 0.0,
+  "max_source_positions": 200,
+  "model_type": "voxtral_encoder",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_mel_bins": 80,
+  "scale_embedding": false,
+  "transformers_version": "5.16.0.dev0",
+  "vocab_size": 99
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe160a71125c8fc9f3f3a3b57b0ac102cc5d0a30bcaad07cc3d35a9a7ab8d09
+size 123888

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aaf3836c2a5332f029ce85a7a62255c966f47b6797ef81dedd0ade9c862e4a8
+size 14894206