clone from WindyWord/listen-windy-lingua-ja via HF->HF (ADR-039 Phase C listen-*)

66b3077 verified 6 days ago

1.62 kB

license: apache-2.0
tags:
  - automatic-speech-recognition
  - whisper
  - windyword
  - japanese
  - ja
library_name: transformers
pipeline_tag: automatic-speech-recognition
language:
  - ja

WindyWord.ai STT — Japanese Lingua (GPU (safetensors))

Transcribes Japanese speech (Japonic).

Note: Quality note: based on whisper-base-japanese (74M params). Small model for a top-10 language; production users may prefer the multilingual openai/whisper-large-v3 for higher accuracy.

Quality

WER: unverified by WindyWord harness yet. Imported from upstream community fine-tune.

About this variant

This is the safetensors deployment format of our Japanese Lingua STT model. Load it via the safetensors/ subfolder.

Part of the WindyWord.ai STT fleet — covering 35+ languages that commercial speech-to-text APIs underserve, with proper dialect / script disclosures where they matter.

Usage

from transformers import WhisperForConditionalGeneration, WhisperProcessor
processor = WhisperProcessor.from_pretrained("WindyWord/listen-windy-lingua-ja", subfolder="safetensors")
model = WhisperForConditionalGeneration.from_pretrained("WindyWord/listen-windy-lingua-ja", subfolder="safetensors")

Commercial Use

Visit windyword.ai for apps and API access.

Provenance & License

Weights derived from upstream community Whisper fine-tunes (see individual model card for exact lineage). Redistributed under Apache-2.0 (inherited).

Certified by Opus 4.6 Opus-Claw (Dr. C) on Veron-1 (RTX 5090, Mt Pleasant SC).