Duplicate from onnx-internal-testing/tiny-random-Nemotron3DiarizationForAudioFrameClassification

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Nemotron3DiarizationForAudioFrameClassification"
+  ],
+  "audio_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "max_position_embeddings": 512,
+    "model_type": "nemotron3_diarization_audio",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "num_mel_bins": 128,
+    "partial_rotary_factor": 1.0,
+    "rope_parameters": {
+      "partial_rotary_factor": 1.0,
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "subsampling_factor": 8
+  },
+  "chunk_length": 4,
+  "chunk_right_context": 1,
+  "dtype": "float32",
+  "fifo_length": 4,
+  "head_config": {
+    "audio_hidden_size": 32,
+    "dtype": "float32",
+    "hidden_size": 16,
+    "model_type": "",
+    "num_speakers": 4,
+    "subsampling_factor": 8
+  },
+  "initializer_range": 0.02,
+  "model_type": "nemotron3_diarization",
+  "speaker_cache_update_period": 3,
+  "streaming_config": {
+    "dtype": "float32",
+    "fifo_length": 4,
+    "latest_frames_score_boost": 0.05,
+    "min_positive_scores_rate": 0.5,
+    "model_type": "",
+    "num_speakers": 4,
+    "prediction_score_threshold": 0.25,
+    "speaker_cache_length": 12,
+    "speaker_cache_silence_frames_per_speaker": 1,
+    "speaker_cache_update_period": 3,
+    "strong_boost_rate": 0.75,
+    "subsampling_factor": 8,
+    "weak_boost_rate": 1.5
+  },
+  "transformers.js_config": {
+    "dtype": "fp32",
+    "use_external_data_format": true
+  },
+  "transformers_version": "5.18.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce1274fdcf36e25b57bc1c2e744108134b66376ebb514a44f7ec4220ef54bf3
+size 232000

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69a4115be1b8150ab2484d5ddc8bfe6ff59d0008c5d87660fb8cfc769bc8902
+size 30063

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1fa4864a150bccaaa9a640e3ac80186aa835776801524dec4a8fae43772c95
+size 257024

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ad72ce432d14a0b42a5cca9aa713319a1928f9ae0b709e1b805a79de030702
+size 35356

onnx/model_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549b10f87cdf5b4e1ce821ef1d17a9fc38a59d5ddcfc92ece2e5a03499deea8a
+size 128000

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "feature_extractor_type": "NemotronAsrStreamingFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 512,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "preemphasis": 0.97,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_length": 400,
+  "processor_class": "Nemotron3DiarizationProcessor"
+}

processor_config.json

@@ -0,0 +1,31 @@
+{
+  "feature_extractor": {
+    "feature_extractor_type": "NemotronAsrStreamingFeatureExtractor",
+    "feature_size": 128,
+    "hop_length": 160,
+    "n_fft": 512,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "preemphasis": 0.97,
+    "return_attention_mask": true,
+    "sampling_rate": 16000,
+    "win_length": 400
+  },
+  "processor_class": "Nemotron3DiarizationProcessor",
+  "streaming_mode": "low_latency",
+  "streaming_modes": {
+    "low_latency": [
+      9,
+      4
+    ],
+    "ultra_low_latency": [
+      3,
+      1
+    ],
+    "very_low_latency": [
+      6,
+      2
+    ]
+  },
+  "subsampling_factor": 8
+}