Upload folder using huggingface_hub

README.md

@@ -0,0 +1,73 @@
+---
+library_name: mlx
+license: mit
+language:
+  - ru
+  - en
+tags:
+  - automatic-speech-recognition
+  - mlx
+  - apple-silicon
+  - russian
+  - gigaam
+  - conformer
+  - ctc
+base_model: ai-sage/GigaAM-v3
+pipeline_tag: automatic-speech-recognition
+model-index:
+  - name: GigaAM-v3-e2e-ctc-mlx
+    results:
+      - task:
+          type: automatic-speech-recognition
+        metrics:
+          - name: RTF (M2 Max)
+            type: rtf
+            value: 0.006
+---
+
+# GigaAM v3 e2e CTC — MLX
+
+MLX port of [GigaAM-v3](https://github.com/salute-developers/GigaAM) for fast Russian speech recognition on Apple Silicon. **180x realtime** on M2 Max.
+
+## Usage
+
+```bash
+pip install gigaam-mlx
+```
+
+```python
+from gigaam_mlx import load_model, transcribe
+
+model, tokenizer = load_model()  # downloads weights automatically
+text = transcribe(model, tokenizer, "recording.wav")
+print(text)
+```
+
+Or via CLI:
+
+```bash
+gigaam-mlx recording.wav
+```
+
+## Performance
+
+MacBook Pro M2 Max, 20-second chunk:
+
+| Backend | Time | Realtime |
+|---|---|---|
+| **MLX CTC (this)** | **0.11s** | **180x** |
+| PyTorch MPS RNNT | 0.76s | 26x |
+| ONNX CPU CTC | 1.66s | 12x |
+
+## Model
+
+- **Architecture:** Conformer (16 layers, 768d, 16 heads, RoPE) + CTC
+- **Parameters:** 220M
+- **Vocabulary:** 257 tokens (SentencePiece)
+- **Features:** Punctuation, text normalization, Russian + English code-switching
+
+## Links
+
+- **Code:** [github.com/aystream/gigaam-mlx](https://github.com/aystream/gigaam-mlx)
+- **Original:** [salute-developers/GigaAM](https://github.com/salute-developers/GigaAM) ([paper](https://arxiv.org/abs/2506.01192))
+- **License:** MIT

config.json

@@ -0,0 +1,32 @@
+{
+  "model_type": "gigaam",
+  "model_variant": "v3_e2e_ctc",
+  "framework": "mlx",
+  "encoder": {
+    "feat_in": 64,
+    "n_layers": 16,
+    "d_model": 768,
+    "n_heads": 16,
+    "ff_expansion_factor": 4,
+    "conv_kernel_size": 5,
+    "subs_kernel_size": 5,
+    "subsampling": "conv1d",
+    "subsampling_factor": 4,
+    "self_attention_model": "rotary",
+    "rope_base": 5000
+  },
+  "head": {
+    "type": "ctc",
+    "num_classes": 257
+  },
+  "preprocessor": {
+    "sample_rate": 16000,
+    "n_mels": 64,
+    "hop_length": 160,
+    "win_length": 320,
+    "n_fft": 320,
+    "center": false
+  },
+  "tokenizer": "tokenizer.model",
+  "total_parameters": 220879361
+}