| --- |
| language: it |
| license: mit |
| tags: |
| - whisper |
| - whisper.cpp |
| - ggml |
| - automatic-speech-recognition |
| - italian |
| - localai |
| - quantized |
| datasets: |
| - mozilla-foundation/common_voice_25_0 |
| - facebook/multilingual_librispeech |
| - facebook/voxpopuli |
| - google/fleurs |
| base_model: openai/whisper-tiny |
| pipeline_tag: automatic-speech-recognition |
| --- |
| |
| # whisper-tiny-it-multi-ggml |
|
|
| [whisper.cpp](https://github.com/ggerganov/whisper.cpp) GGML quantizations of [LocalAI-io/whisper-tiny-it-multi](https://huggingface.co/LocalAI-io/whisper-tiny-it-multi) for fast CPU/GPU inference. |
|
|
| **Author:** Ettore Di Giacinto |
|
|
| Brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team. These models can be used directly with [LocalAI](https://localai.io) and any whisper.cpp-based runtime. |
|
|
| ## Files |
|
|
| | File | Quantization | Description | |
| |------|--------------|-------------| |
| | `ggml-model-f16.bin` | float16 | Full precision (no quantization) — highest quality | |
| | `ggml-model-q8_0.bin` | int8 | 8-bit quantization — minimal quality loss | |
| | `ggml-model-q5_0.bin` | int5 | 5-bit quantization — good quality/size tradeoff | |
| | `ggml-model-q4_0.bin` | int4 | 4-bit quantization — smallest size, fastest | |
|
|
| ## Training |
|
|
| Fine-tuned [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) (39M params) on **Common Voice 25.0 + MLS + VoxPopuli + FLEURS Italian**. |
|
|
| See [LocalAI-io/whisper-tiny-it-multi](https://huggingface.co/LocalAI-io/whisper-tiny-it-multi) for the full safetensors model and detailed WER results. |
|
|
| ## Usage |
|
|
| ### whisper.cpp |
|
|
| ```bash |
| # Download a quant |
| huggingface-cli download LocalAI-io/whisper-tiny-it-multi-ggml ggml-model-q5_0.bin --local-dir . |
| |
| # Run |
| ./whisper-cli -m ggml-model-q5_0.bin -f audio.wav -l it |
| ``` |
|
|
| ### whisper.cpp Python bindings (pywhispercpp) |
|
|
| ```python |
| from pywhispercpp.model import Model |
| |
| model = Model("ggml-model-q5_0.bin", language="it") |
| segments = model.transcribe("audio.wav") |
| for seg in segments: |
| print(seg.text) |
| ``` |
|
|
| ### LocalAI |
|
|
| ```yaml |
| # In your LocalAI model config |
| name: whisper-tiny-it-multi |
| backend: whisper |
| parameters: |
| model: ggml-model-q5_0.bin |
| ``` |
|
|
| ## Links |
|
|
| - **HF Safetensors:** [LocalAI-io/whisper-tiny-it-multi](https://huggingface.co/LocalAI-io/whisper-tiny-it-multi) |
| - **CTranslate2 INT8:** [LocalAI-io/whisper-tiny-it-multi-ct2-int8](https://huggingface.co/LocalAI-io/whisper-tiny-it-multi-ct2-int8) |
| - **Code:** [github.com/localai-org/whisper-it](https://github.com/localai-org/whisper-it) |
| - **whisper.cpp:** [github.com/ggerganov/whisper.cpp](https://github.com/ggerganov/whisper.cpp) |
| - **LocalAI:** [github.com/mudler/LocalAI](https://github.com/mudler/LocalAI) |
|
|
