publish whisper-large-v3-turbo OpenASR packs

.gitattributes

@@ -0,0 +1 @@
+*.oasr filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,114 @@
+---
+license: mit
+base_model: openai/whisper-large-v3-turbo
+pipeline_tag: automatic-speech-recognition
+library_name: openasr
+tags:
+  - automatic-speech-recognition
+  - speech-to-text
+  - openasr
+  - oasr
+  - whisper-turbo
+---
+
+<div align="center">
+
+# Whisper Large v3 Turbo · OpenASR
+
+**Fast multilingual Whisper built from pruned large-v3**
+
+[![License](https://img.shields.io/badge/license-MIT-2563eb.svg)](https://github.com/openai/whisper/blob/main/LICENSE)
+[![Format](https://img.shields.io/badge/format-.oasr-7c3aed.svg)](https://github.com/QuintinShaw/openasr)
+[![Runtime](https://img.shields.io/badge/runtime-OpenASR-111827.svg)](https://openasr.org)
+[![Base model](https://img.shields.io/badge/base-whisper--large--v3--turbo-f59e0b.svg)](https://huggingface.co/openai/whisper-large-v3-turbo)
+
+Native speech-to-text in the **[OpenASR](https://github.com/QuintinShaw/openasr)** runtime —
+engineered for peak performance on CPU & GPU, **no Python at inference time**.
+
+</div>
+
+---
+
+## ✨ Highlights
+
+- ⚡ **Turbo decoder** — prunes Whisper large-v3's decoder from 32 layers to 4 for much faster generation
+- 🌍 **Multilingual ASR** — transcribes many languages and can translate speech to English
+- 🎙️ **Zero-shot robustness** — inherits Whisper's large-scale weak-supervision training across noisy domains
+- 🦀 **Native in OpenASR** — `.oasr` packs run with no Python at inference, engineered for peak performance on CPU & GPU
+
+## 🚀 Quickstart
+
+```bash
+# 1. Install the OpenASR CLI  ·  https://openasr.org
+# 2. Pull a build (pick a quant — see the table below)
+openasr pull whisper-large-v3-turbo:q8
+
+# 3. Transcribe
+openasr transcribe audio.wav --model whisper-large-v3-turbo
+```
+
+All builds for this model:
+
+```bash
+openasr pull whisper-large-v3-turbo:fp16
+openasr pull whisper-large-v3-turbo:q8
+openasr pull whisper-large-v3-turbo:q4
+```
+
+## 📦 Available builds
+
+| Quant | File (`.oasr`) | Size | RAM peak | RTF · M1 CPU | RTF · M1 GPU | JFK ΔWER vs fp16 |
+|:------|:---------------|-----:|---------:|-------------:|-------------:|-----------------:|
+| fp16 | `whisper-large-v3-turbo-fp16.oasr` | 1.62 GB | 3.62 GB | 0.52× | 0.39× | 0.0% |
+| q8_0 | `whisper-large-v3-turbo-q8_0.oasr` | 931 MB | 2.28 GB | 0.52× | 0.35× | 0.0% |
+| q4_k | `whisper-large-v3-turbo-q4_k.oasr` | 564 MB | 1.54 GB | 0.51× | 0.25× | 0.0% |
+
+<sub>RTF = real-time factor on the fixed 11s JFK clip (**lower is faster**); RAM peak measured per pack
+in an isolated subprocess. JFK ΔWER compares each quantized build's JFK transcript to this model's
+fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy.
+**q8_0** is the recommended default — near-reference quality at a fraction of the
+footprint.</sub>
+
+## 🧠 About Whisper Large v3 Turbo
+
+Whisper Large v3 Turbo is OpenAI's faster variant of Whisper large-v3: it keeps the same
+Whisper architecture and multilingual speech-recognition/translation interface, but reduces
+the decoder depth from 32 layers to 4. The upstream card describes the result as much faster
+with only a minor quality trade-off, while retaining Whisper's broad zero-shot behavior from
+training on more than five million hours of labeled audio. This OpenASR repo repackages the
+original `openai/whisper-large-v3-turbo` weights as `.oasr` packs that run natively in the
+OpenASR runtime with no Python at inference time. For most users the q8_0 build is the
+recommended default; q4_k is for tighter memory budgets and fp16 is for verification or
+maximum fidelity.
+
+## ⚙️ How these packs were made
+
+Converted from [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) with the OpenASR importer:
+
+```bash
+openasr model-pack import whisper <src> <out>.oasr \
+  --package-id whisper-large-v3-turbo --quantization {fp16,q8-0,q4-k}
+```
+
+The `.oasr` container is GGUF-backed; packs use zero-copy mmap weight binding and graph
+buffer reuse to keep peak memory low.
+
+## ⚖️ License
+
+These packs **inherit the upstream model's license: MIT**
+([source](https://github.com/openai/whisper/blob/main/LICENSE)). OpenASR packaging retains the upstream copyright and
+NOTICE; the only modifications are format conversion and quantization.
+
+## 🙏 Acknowledgements
+
+This pack is a redistribution of **Whisper Large v3 Turbo**, released by **OpenAI**
+([openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo)).
+All credit for the original model, training recipe, and weights belongs to OpenAI. The packs
+inherit the upstream MIT license; OpenASR only converts the weights into `.oasr` packages and
+adds quantized builds for local runtime use.
+
+## 🔗 Links
+
+- 🦀 **OpenASR** — <https://github.com/QuintinShaw/openasr>
+- 🌐 **Website** — <https://openasr.org>
+- 🤗 **Upstream model** — [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo)

whisper-large-v3-turbo-fp16.oasr

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c963b06ceb623f45d6661cbbe97c861764fb273a0cc0a2cbe5c44b536c42a3bf
+size 1619471168

whisper-large-v3-turbo-q4_k.oasr

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d67adbf377e75a10104b2f8ab31b30e83950f888a16a58c968b258c78c443967
+size 878914304

whisper-large-v3-turbo-q8_0.oasr

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aadbdd35ab260d127f50affaecae0a51f5793e700afe212cefb0e74a99f95da
+size 931343168