|
Download README.md from basecompute/whisper-tiny: direct link, hf CLI and curl.
- Browser
- Download file 1.92 kB
-
https://huggingface.co/basecompute/whisper-tiny/resolve/main/README.md
- Command line
-
hf download hf://basecompute/whisper-tiny/README.md
-
curl -L -o README.md https://huggingface.co/basecompute/whisper-tiny/resolve/main/README.md
1.92 kB
| license: apache-2.0 | |
| base_model: openai/whisper-tiny | |
| library_name: basert | |
| pipeline_tag: automatic-speech-recognition | |
| tags: | |
| - basert | |
| - apple-silicon | |
| - whisper | |
| - speech-recognition | |
| # whisper-tiny | |
| [BaseRT](https://github.com/basecompute/baseRT) `.base` build of | |
| [`openai/whisper-tiny`](https://huggingface.co/openai/whisper-tiny), | |
| OpenAI's 39M-parameter Whisper speech-recognition model, | |
| for fast local transcription on Apple Silicon. | |
| ## Files | |
| | File | Precision | Size | | |
| |------|-----------|------| | |
| | `whisper-tiny-F16.base` | float16 | 79 MB | | |
| | `whisper-tiny-Q8.base` | 8-bit linears, f16 embeddings/conv/norms | 63 MB | | |
| | `whisper-tiny-Q4.base` | 4-bit linears, f16 embeddings/conv/norms | 55 MB | | |
| F16 and Q8 are transcription-quality equivalent (Q8 passes the same | |
| word-error parity gates against reference openai-whisper). Q4 is the | |
| smallest and remains accurate; on some smaller variants it can | |
| occasionally repeat a word in timestamped beam decoding. | |
| ## Usage | |
| ```bash | |
| curl -LsSf https://basecompute.co/install.sh | sh | |
| basert serve --model whisper-tiny-F16.base | |
| ``` | |
| `POST /v1/audio/transcriptions` (multipart or JSON) returns `json`, `text`, | |
| `srt`, `vtt`, or `verbose_json` (with per-segment `avg_logprob` / | |
| `no_speech_prob` / `compression_ratio` / `temperature` and the detected | |
| `language`), with optional SSE streaming and `POST /v1/audio/translations`. Supported | |
| request fields: `language` (or `"auto"` to detect), `prompt` | |
| (initial prompt / vocabulary bias), `task` (`transcribe`/`translate`). Or transcribe directly | |
| from the CLI: | |
| ```bash | |
| basert-transcribe whisper-tiny-F16.base audio.wav --lang auto | |
| ``` | |
| Multilingual: pass `language` (e.g. `--lang de`), or `auto` to detect, across the 99 supported languages. `task=translate` produces English from any source language (also via `POST /v1/audio/translations`). | |
| Released under the apache-2.0 license, inherited from the base model. | |