Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,43 @@
+---
+license: apache-2.0
+base_model: openai/whisper-small
+library_name: basert
+pipeline_tag: automatic-speech-recognition
+tags:
+  - basert
+  - apple-silicon
+  - whisper
+  - speech-recognition
+---
+
+# whisper-small
+
+[BaseRT](https://github.com/basecompute/baseRT) `.base` build of
+[`openai/whisper-small`](https://huggingface.co/openai/whisper-small),
+OpenAI's 244M-parameter Whisper speech-recognition model,
+for fast local transcription on Apple Silicon.
+
+## Files
+
+| File | Precision | Size |
+|------|-----------|------|
+| `whisper-small-F16.base` | float16 | 489 MB |
+
+## Usage
+
+```bash
+curl -LsSf https://basecompute.co/install.sh | sh
+basert serve --model whisper-small-F16.base
+```
+
+`POST /v1/audio/transcriptions` (multipart or JSON) returns `json`, `text`,
+`srt`, `vtt`, or `verbose_json`, with optional SSE streaming. Or transcribe
+directly from the CLI:
+
+```bash
+basert-transcribe whisper-small-F16.base audio.wav
+```
+
+Multilingual: pass `language` (e.g. `--lang de`) to select any of the 99 supported languages.
+
+Released under the apache-2.0 license, inherited from the base model.