Upload folder using huggingface_hub

README.md

@@ -0,0 +1,41 @@
+---
+license: mit
+tags:
+  - mlx
+  - 4bit
+  - whisper
+  - stt
+  - metalrt
+  - apple-silicon
+---
+
+# Whisper Medium — MLX 4-bit Quantized
+
+Custom MLX 4-bit quantization of [OpenAI Whisper Medium](https://huggingface.co/openai/whisper-medium) optimized for [MetalRT](https://github.com/RunanywhereAI/metalrt-binaries) GPU inference on Apple Silicon.
+
+## Usage
+
+Used by [RCLI](https://github.com/RunanywhereAI/RCLI) with the MetalRT engine for speech-to-text:
+
+```bash
+rcli setup          # select MetalRT or Both engines
+```
+
+> **Note**: Whisper Medium is in GPU beta. Whisper Tiny is recommended for production use.
+
+## Performance (Apple M3 Max)
+
+| Metric | Value |
+|--------|-------|
+| Latency (1.2s audio) | 233 ms |
+| RTF | 0.19x |
+| Quantization | MLX 4-bit |
+
+## License
+
+Model weights: [MIT](https://github.com/openai/whisper/blob/main/LICENSE) (OpenAI)
+MetalRT engine: [Proprietary](https://github.com/RunanywhereAI/metalrt-binaries/blob/main/LICENSE) (RunAnywhere, Inc.)
+
+## Contact
+
+founder@runanywhere.ai | https://runanywhere.ai

config.json

@@ -0,0 +1,17 @@
+{
+    "n_mels": 80,
+    "n_audio_ctx": 1500,
+    "n_audio_state": 1024,
+    "n_audio_head": 16,
+    "n_audio_layer": 24,
+    "n_vocab": 51865,
+    "n_text_ctx": 448,
+    "n_text_state": 1024,
+    "n_text_head": 16,
+    "n_text_layer": 24,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "model_type": "whisper"
+}

whisper-medium-mlx-4bit/.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

whisper-medium-mlx-4bit/README.md

@@ -0,0 +1 @@
+Quantized to 4-bit whisper medium

whisper-medium-mlx-4bit/config.json

@@ -0,0 +1,17 @@
+{
+    "n_mels": 80,
+    "n_audio_ctx": 1500,
+    "n_audio_state": 1024,
+    "n_audio_head": 16,
+    "n_audio_layer": 24,
+    "n_vocab": 51865,
+    "n_text_ctx": 448,
+    "n_text_state": 1024,
+    "n_text_head": 16,
+    "n_text_layer": 24,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "model_type": "whisper"
+}

whisper-medium-mlx-4bit/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7003ac6761e152604cbf8129c611b6cc4720f10dfdcbf36f54a2f6aaa589b64a
+size 511900792

whisper-medium-mlx-4bit/weights.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e89f26c4d89721881f4a415d9d525b548f93e95f8b044098f0da84c2582f601
+size 512230640