Model card

README.md

@@ -1,27 +1,71 @@
 ---
 license: apache-2.0
 base_model: openai/whisper-tiny
+pipeline_tag: automatic-speech-recognition
+library_name: onnx
 tags:
 - dakera
+- ai-agent-memory
+- agent-memory
+- long-term-memory
+- rag
+- self-hosted
+- mcp
+- onnx
 - mirror
 ---
 
-# whisper-tiny
+<p align="center">
+  <a href="https://dakera.ai"><img src="https://dakera.ai/assets/logo-128.png" width="96" alt="Dakera logo"></a>
+</p>
 
-An unmodified copy of the files [Dakera](https://dakera.ai) downloads for [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny), so Dakera installs keep working if an upstream repository moves or goes away. Dakera downloads from here first and falls back to the original repositories; both are checked against the same SHA-256.
+<h1 align="center">whisper-tiny</h1>
 
-The model is by OpenAI, released under the Apache-2.0 licence. All credit goes to its authors: see the [original model card](https://huggingface.co/openai/whisper-tiny) for what it does, how it was trained, and how to cite it.
+<p align="center"><b>Speech-to-text for Dakera · a verified mirror by Dakera, the self-hosted memory engine for AI agents</b></p>
+
+<p align="center">
+  <a href="https://dakera.ai"><img alt="Dakera: dakera.ai" src="https://img.shields.io/badge/Dakera-dakera.ai-c9a227?style=flat-square"></a> <a href="https://dakera.ai/docs"><img alt="Docs: dakera.ai/docs" src="https://img.shields.io/badge/Docs-dakera.ai%2Fdocs-0b0b0b?style=flat-square"></a> <a href="https://github.com/Dakera-AI"><img alt="GitHub: Dakera-AI" src="https://img.shields.io/badge/GitHub-Dakera--AI-181717?style=flat-square&logo=github&logoColor=white"></a> <a href="https://huggingface.co/DakeraAI/whisper-tiny/blob/main/LICENSE"><img alt="License: Apache-2.0" src="https://img.shields.io/badge/License-Apache--2.0-2b6cb0?style=flat-square"></a> <a href="https://huggingface.co/openai/whisper-tiny"><img alt="Original: openai/whisper-tiny" src="https://img.shields.io/badge/Original-openai%2Fwhisper--tiny-6b7280?style=flat-square"></a>
+</p>
+
+
+> An unmodified, checksum-verified copy of the files [Dakera](https://dakera.ai) uses from [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny). The model is by **OpenAI**; all credit goes to its authors.
+
+## In Dakera
+
+Transcribes audio attachments into searchable memories (`DAKERA_ATTACHMENTS=true`, `DAKERA_WHISPER_MODEL=whisper-tiny`).
+
+Dakera fetches this speech recognition from this repository first and from the original repositories if it is unreachable, so installs never depend on a single source. Both are checked against the same SHA-256, and the [Dakera Docker image](https://github.com/Dakera-AI/dakera-deploy) ships the default models ready to run, with no download at startup.
 
 ## Files
 
 Copied byte for byte from:
 
-| File | Copied from | SHA-256 | Bytes |
+| File | Source | SHA-256 | Bytes |
 |---|---|---|---|
 | `onnx/decoder_model.onnx` | [onnx-community/whisper-tiny](https://huggingface.co/onnx-community/whisper-tiny) | `ab79e3f2a9a3d98f159f853a3172120a38af7eb5f7863d706aa7d39c228f009e` | 118,397,483 |
 | `onnx/encoder_model.onnx` | [onnx-community/whisper-tiny](https://huggingface.co/onnx-community/whisper-tiny) | `6642befb640f950d4a8cbbd17834d59e7e75f575b81ccf213e06b050623ab1dd` | 32,904,992 |
-| `tokenizer.json` | [onnx-community/whisper-tiny](https://huggingface.co/onnx-community/whisper-tiny) | `text file` | 2,480,466 |
+| `tokenizer.json` | [onnx-community/whisper-tiny](https://huggingface.co/onnx-community/whisper-tiny) | `27fc476bfe7f17299480be2273fc0608e4d5a99aba2ab5dec5374b4482d1a566` | 2,480,466 |
+
+## Licence and credit
+
+Apache-2.0, the same as the original model (see [`LICENSE`](https://huggingface.co/DakeraAI/whisper-tiny/blob/main/LICENSE)). For what the model does, how it was trained and how to cite it, see the [original model card](https://huggingface.co/openai/whisper-tiny).
+
+## About Dakera
+
+**[Dakera](https://dakera.ai) is a self-hosted memory engine for AI agents.** It gives agents long-term memory that survives sessions: hybrid vector and full-text retrieval, reranking, entity extraction and importance decay, in a single Rust binary that runs on your own servers, with an MCP server for Claude, Cursor and other agents. 88.2% Recall@20 on the LoCoMo long-term memory benchmark.
+
+```bash
+docker run -p 3000:3000 -e DAKERA_ROOT_API_KEY=dk-mykey ghcr.io/dakera-ai/dakera:latest
+```
 
-## Licence
+| | |
+|---|---|
+| 🌐 Website | [dakera.ai](https://dakera.ai) |
+| 📚 Documentation | [dakera.ai/docs](https://dakera.ai/docs) |
+| 💻 GitHub | [github.com/Dakera-AI](https://github.com/Dakera-AI) |
+| 🚀 Self-hosting (Docker, Kubernetes, Helm) | [dakera-deploy](https://github.com/Dakera-AI/dakera-deploy) |
+| 🔌 MCP server | [dakera-mcp](https://github.com/Dakera-AI/dakera-mcp) |
+| 🧰 SDKs | [Python](https://github.com/Dakera-AI/dakera-py) · [TypeScript](https://github.com/Dakera-AI/dakera-js) · [Go](https://github.com/Dakera-AI/dakera-go) · [Rust](https://github.com/Dakera-AI/dakera-rs) |
+| 💼 LinkedIn | [Dakera AI](https://www.linkedin.com/company/dakera-ai) |
 
-Apache-2.0, the same as the original model (see `LICENSE`).
+Questions or feedback: [amine@dakera.ai](mailto:amine@dakera.ai).