| --- |
| language: it |
| license: mit |
| tags: |
| - whisper |
| - automatic-speech-recognition |
| - italian |
| - ctranslate2 |
| - faster-whisper |
| - whisperx |
| - localai |
| - int8 |
| datasets: |
| - mozilla-foundation/common_voice_25_0 |
| base_model: openai/whisper-base |
| pipeline_tag: automatic-speech-recognition |
| --- |
| |
| # whisper-base-it-multi-yodas-asr_only-nocv-ct2-int8 |
| |
| [CTranslate2](https://github.com/OpenNMT/CTranslate2) INT8 quantized version of [LocalAI-io/whisper-base-it-multi-yodas-asr_only-nocv](https://huggingface.co/LocalAI-io/whisper-base-it-multi-yodas-asr_only-nocv) for fast CPU inference. |
| |
| **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 |
| |
| - **Base model:** openai/whisper-base, fine-tuned on MLS + VoxPopuli + YODAS-Granary (asr_only) Italian |
| - **Quantization:** INT8 via CTranslate2 |
|
|
| ## Usage |
|
|
| ### faster-whisper |
|
|
| ```python |
| from faster_whisper import WhisperModel |
| |
| model = WhisperModel("LocalAI-io/whisper-base-it-multi-yodas-asr_only-nocv-ct2-int8", device="cpu", compute_type="int8") |
| segments, info = model.transcribe("audio.mp3", language="it") |
| for segment in segments: |
| print(f"[{segment.start:.1f}s - {segment.end:.1f}s] {segment.text}") |
| ``` |
|
|
| ### WhisperX |
|
|
| ```python |
| import whisperx |
| |
| model = whisperx.load_model("LocalAI-io/whisper-base-it-multi-yodas-asr_only-nocv-ct2-int8", device="cpu", compute_type="int8") |
| result = model.transcribe("audio.mp3", language="it") |
| ``` |
|
|
| ## Links |
|
|
| - **HF Safetensors:** [LocalAI-io/whisper-base-it-multi-yodas-asr_only-nocv](https://huggingface.co/LocalAI-io/whisper-base-it-multi-yodas-asr_only-nocv) |
| - **Code:** [github.com/mudler/italian-asr](https://github.com/mudler/italian-asr) |
| - **LocalAI:** [github.com/mudler/LocalAI](https://github.com/mudler/LocalAI) |
|
|
