Whisper Medium Lv Late ONNX
This is an ONNX version of AiLab-IMCS-UL/whisper-medium-lv-late. It was automatically converted and uploaded using this Hugging Face Space.
Fuente del modelo
- Tipo
- Text model
- Tamaño del archivo
- 478 MB
- Modelo base
- AiLab-IMCS-UL/whisper-medium-lv-late
- Versión
- vdecoder_model_bnb4
- Actualizado
- 27 sept 2026
- Descargas
- 13
- Fuente
- Hugging Face
Descripción de la fuente
whisper-medium-lv-late (ONNX)
This is an ONNX version of AiLab-IMCS-UL/whisper-medium-lv-late. It was automatically converted and uploaded using this Hugging Face Space.
Usage with Transformers.js
See the pipeline documentation for automatic-speech-recognition: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.AutomaticSpeechRecognitionPipeline
This model is a fine-tuned version of openai/whisper-medium on more than 20 hours of diverse Latvian broadcast data.
Test WER: 15.9%
Fuentes
1 fuente
Fuentes
1 fuenteVerificado 30 ago
Download files
Artefactos del modelo
2 artefactos
Artefactos del modelo
2 artefactosonnx/decoder_model_q4.onnx
onnx · Q4 (unverified) · 478 MB · SHA-256 b3cb7694e93e…1c04 · Hugging Face
Download fileExtractos de fuentes
2 extractos
Extractos de fuentes
2 extractos--- license: apache-2.0 language: - lv pipeline_tag: automatic-speech-recognition metrics: - wer library_name: transformers.js base_model: - AiLab-IMCS-UL/whisper-medium-lv-late --- # whisper-medium-lv-late (ONNX) This is an ONNX version of [AiLab-IMCS-UL/whisper-medium-lv-late](https://huggingface.co/AiLab-IMCS-UL/whisper-medium-lv-late). It was automatically converted and uploaded using [this Hugging Face Space](https://huggingface.co/spaces/onnx-community/convert-to-onnx). ## Usage with Transformers.js See the pipeline documentation for `automatic-speech-recognition`: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.AutomaticSpeechRecognitionPipeline --- This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on more than 20 hours of diverse Latvian broadcast data. Test WER: 15.9%
Source context: 13 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers.js · Repo onnx-community/whisper-medium-lv-late-ONNX
