| language: it | |
| license: mit | |
| tags: | |
| - whisper | |
| - automatic-speech-recognition | |
| - italian | |
| - localai | |
| datasets: | |
| - mozilla-foundation/common_voice_25_0 | |
| base_model: openai/whisper-tiny | |
| pipeline_tag: automatic-speech-recognition | |
| # whisper-tiny-it-yodas-only | |
| Fine-tuned [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) for Italian automatic speech recognition (ASR). | |
| **Author:** Ettore Di Giacinto | |
| Brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team. This model can be used directly with [LocalAI](https://localai.io). | |
| ## Training Details | |
| - **Base model:** openai/whisper-tiny | |
| - **Dataset:** YODAS-Granary Italian (asr_only + ast capped at 200000) | |
| - **Steps:** 10,000 | |
| - **Precision:** bf16 | |
| ## Usage | |
| ### Transformers | |
| ```python | |
| from transformers import pipeline | |
| pipe = pipeline("automatic-speech-recognition", model="LocalAI-io/whisper-tiny-it-yodas-only") | |
| result = pipe("audio.mp3", generate_kwargs={"language": "it", "task": "transcribe"}) | |
| print(result["text"]) | |
| ``` | |
| ### CTranslate2 / faster-whisper (INT8, optimized for CPU) | |
| See: [LocalAI-io/whisper-tiny-it-yodas-only-ct2-int8](https://huggingface.co/LocalAI-io/whisper-tiny-it-yodas-only-ct2-int8) | |
| ## Links | |
| - **CTranslate2 INT8:** [LocalAI-io/whisper-tiny-it-yodas-only-ct2-int8](https://huggingface.co/LocalAI-io/whisper-tiny-it-yodas-only-ct2-int8) | |
| - **Code:** [github.com/mudler/italian-asr](https://github.com/mudler/italian-asr) | |
| - **LocalAI:** [github.com/mudler/LocalAI](https://github.com/mudler/LocalAI) | |