Duplicate from aufklarer/Silero-VAD-v5-MLX

Co-authored-by: Ivan <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+tags:
+  - mlx
+  - voice-activity-detection
+  - silero
+  - vad
+  - streaming
+  - apple-silicon
+base_model: snakers4/silero-vad
+library_name: mlx
+pipeline_tag: voice-activity-detection
+---
+
+# Silero VAD v5 — MLX
+
+MLX-compatible weights for [Silero VAD v5](https://github.com/snakers4/silero-vad), converted from the official JIT model.
+
+## Model
+
+Silero VAD v5 is a lightweight (~309K params) voice activity detection model that processes 512-sample chunks (32ms @ 16kHz) with sub-millisecond latency. It outputs a speech probability between 0 and 1 for each chunk, with LSTM state carried across chunks for streaming operation.
+
+**Architecture:** STFT → 4×Conv1d+ReLU encoder → LSTM(128) → Conv1d decoder → sigmoid
+
+## Usage (Swift / MLX)
+
+```swift
+import SpeechVAD
+
+// Load model
+let vad = try await SileroVADModel.fromPretrained()
+
+// Streaming: process 512-sample chunks
+let prob = vad.processChunk(samples)  // → 0.0...1.0
+
+// Batch: detect speech segments in complete audio
+let segments = vad.detectSpeech(audio: samples, sampleRate: 16000)
+for seg in segments {
+    print("Speech: \(seg.startTime)s - \(seg.endTime)s")
+}
+```
+
+Part of [qwen3-asr-swift](https://github.com/nicklama/qwen3-asr-swift).
+
+## Conversion
+
+```bash
+python3 scripts/convert_silero_vad.py --upload
+```
+
+Converts the official Silero VAD v5 JIT model via `torch.hub`, transposes Conv1d weights for MLX channels-last format, sums LSTM biases (`bias_ih + bias_hh`), and saves as safetensors.
+
+## Weight Mapping
+
+| JIT Key | MLX Key | Shape |
+|---------|---------|-------|
+| `_model.stft.forward_basis_buffer` | `stft.weight` | [258, 256, 1] |
+| `_model.encoder.{i}.reparam_conv.weight` | `encoder.{i}.weight` | varies |
+| `_model.encoder.{i}.reparam_conv.bias` | `encoder.{i}.bias` | varies |
+| `_model.decoder.rnn.weight_ih` | `lstm.Wx` | [512, 128] |
+| `_model.decoder.rnn.weight_hh` | `lstm.Wh` | [512, 128] |
+| `_model.decoder.rnn.bias_ih + bias_hh` | `lstm.bias` | [512] |
+| `_model.decoder.decoder.2.weight` | `decoder.weight` | [1, 1, 128] |
+| `_model.decoder.decoder.2.bias` | `decoder.bias` | [1] |
+
+## License
+
+The original Silero VAD model is released under the [MIT License](https://github.com/snakers4/silero-vad/blob/master/LICENSE).

config.json

@@ -0,0 +1,29 @@
+{
+  "model_type": "silero_vad_v5",
+  "sample_rate": 16000,
+  "chunk_size": 512,
+  "context_size": 64,
+  "filter_length": 256,
+  "hop_length": 128,
+  "encoder_channels": [
+    129,
+    128,
+    64,
+    64,
+    128
+  ],
+  "encoder_kernel_sizes": [
+    3,
+    3,
+    3,
+    3
+  ],
+  "encoder_strides": [
+    1,
+    2,
+    2,
+    1
+  ],
+  "lstm_hidden_size": 128,
+  "lstm_num_layers": 1
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704e4211eab4177b88dd7f2f0746f53cc737d49711d34c4a34d00950bb78201b
+size 1237580