| --- |
| language: en |
| license: apache-2.0 |
| library_name: ctranslate2 |
| pipeline_tag: automatic-speech-recognition |
| tags: |
| - whisper |
| - ctranslate2 |
| - speech-recognition |
| - transcription |
| - bfloat16 |
| base_model: openai/whisper-tiny |
| --- |
| |
| # π£οΈ Whisper Tiny β CTranslate2 (`bfloat16`) |
|
|
| This is [OpenAI's whisper-tiny](https://huggingface.co/openai/whisper-tiny) converted to [CTranslate2](https://github.com/OpenNMT/CTranslate2) format with `bfloat16` precision. |
|
|
| > [!TIP] |
| > Also available in other precisions: |
| > [`float32`](https://huggingface.co/ctranslate2-4you/whisper-tiny-ct2-float32) Β· [`float16`](https://huggingface.co/ctranslate2-4you/whisper-tiny-ct2-float16) |
|
|
| --- |
|
|
| ## π Details |
|
|
| | | | |
| |---|---| |
| | **Base model** | [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | |
| | **Format** | CTranslate2 | |
| | **Precision** | `bfloat16` | |
| | **Language** | Multilingual | |
| | **Task** | Automatic Speech Recognition | |
|
|
| --- |
|
|
| ## β‘ Quick Start |
|
|
| Install the inference library: |
|
|
| ```bash |
| pip install whisper-s2t-reborn |
| ``` |
|
|
| Transcribe an audio file: |
|
|
| ```python |
| import whisper_s2t |
| |
| model = whisper_s2t.load_model( |
| model_identifier="tiny", |
| compute_type="bfloat16", |
| device="cuda", |
| ) |
| |
| result = model.transcribe_with_vad( |
| ["audio.wav"], |
| lang_codes=["en"], |
| tasks=["transcribe"], |
| initial_prompts=[None], |
| batch_size=1, # increase this to significantly improve throughput |
| ) |
| |
| for segment in result[0]: |
| print(segment["text"]) |
| ``` |
|
|
| > [!NOTE] |
| > Models are **auto-downloaded** from this repo the first time you run inference. No manual download required. |
|
|
| *See the [whisper-s2t-reborn](https://github.com/BBC-Esq/WhisperS2T-reborn) repository for the full list of available parameters.* |
|
|
| --- |
|
|
| ## π¦ All Available CTranslate2 Whisper Models |
|
|
| Every model below is hosted at [huggingface.co/ctranslate2-4you](https://huggingface.co/ctranslate2-4you) and works with [whisper-s2t-reborn](https://github.com/BBC-Esq/WhisperS2T-reborn). |
|
|
| ### π Standard Whisper (Multilingual) |
|
|
| | Model | `float32` | `float16` | `bfloat16` | |
| |---|:---:|:---:|:---:| |
| | **tiny** | [Link](https://huggingface.co/ctranslate2-4you/whisper-tiny-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-tiny-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-tiny-ct2-bfloat16) | |
| | **base** | [Link](https://huggingface.co/ctranslate2-4you/whisper-base-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-base-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-base-ct2-bfloat16) | |
| | **small** | [Link](https://huggingface.co/ctranslate2-4you/whisper-small-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-small-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-small-ct2-bfloat16) | |
| | **medium** | [Link](https://huggingface.co/ctranslate2-4you/whisper-medium-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-medium-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-medium-ct2-bfloat16) | |
| | **large-v3** | [Link](https://huggingface.co/ctranslate2-4you/whisper-large-v3-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-large-v3-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-large-v3-ct2-bfloat16) | |
|
|
| ### πΊπΈ Whisper English-Only |
|
|
| | Model | `float32` | `float16` | `bfloat16` | |
| |---|:---:|:---:|:---:| |
| | **tiny.en** | [Link](https://huggingface.co/ctranslate2-4you/whisper-tiny.en-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-tiny.en-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-tiny.en-ct2-bfloat16) | |
| | **base.en** | [Link](https://huggingface.co/ctranslate2-4you/whisper-base.en-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-base.en-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-base.en-ct2-bfloat16) | |
| | **small.en** | [Link](https://huggingface.co/ctranslate2-4you/whisper-small.en-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-small.en-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-small.en-ct2-bfloat16) | |
| | **medium.en** | [Link](https://huggingface.co/ctranslate2-4you/whisper-medium.en-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-medium.en-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-medium.en-ct2-bfloat16) | |
|
|
| ### β‘ Distilled Whisper |
|
|
| | Model | `float32` | `float16` | `bfloat16` | |
| |---|:---:|:---:|:---:| |
| | **distil-small.en** | [Link](https://huggingface.co/ctranslate2-4you/distil-whisper-small.en-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/distil-whisper-small.en-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/distil-whisper-small.en-ct2-bfloat16) | |
| | **distil-medium.en** | [Link](https://huggingface.co/ctranslate2-4you/distil-whisper-medium.en-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/distil-whisper-medium.en-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/distil-whisper-medium.en-ct2-bfloat16) | |
| | **distil-large-v3** | [Link](https://huggingface.co/ctranslate2-4you/distil-whisper-large-v3-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/distil-whisper-large-v3-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/distil-whisper-large-v3-ct2-bfloat16) | |
|
|
| ### π Whisper Large-v3 Turbo |
|
|
| | Model | `float32` | `float16` | `bfloat16` | |
| |---|:---:|:---:|:---:| |
| | **large-v3-turbo** | [Link](https://huggingface.co/ctranslate2-4you/whisper-large-v3-turbo-ct2-float32) | [Link](https://huggingface.co/ctranslate2-4you/whisper-large-v3-turbo-ct2-float16) | [Link](https://huggingface.co/ctranslate2-4you/whisper-large-v3-turbo-ct2-bfloat16) | |
|
|
| --- |
|
|
| ## π Links |
|
|
| - π¦ **Inference library** β [whisper-s2t-reborn](https://github.com/BBC-Esq/WhisperS2T-reborn) |
| - ποΈ **CTranslate2** β [github.com/OpenNMT/CTranslate2](https://github.com/OpenNMT/CTranslate2) |
| - π§ **Original model** β [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) |
|
|