Refresh README — uniform WindyWord template with WER tier + dialect notes

README.md

@@ -6,7 +6,6 @@ tags:
 - windyword
 - english
 - multilingual
-- multilingual-fallback
 library_name: transformers
 pipeline_tag: automatic-speech-recognition
 language:
@@ -16,32 +15,13 @@ language:
 
 # WindyWord.ai STT — Windy Pro Engine
 
-**The flagship multilingual speech-to-text engine. Transcribes audio in 99+ languages with state-of-the-art quality.**
-
-## Recommended fallback for low-resource languages
-
-This is the **multilingual fallback model** for the WindyWord STT fleet. When a language-specific Lingua model is missing or underperforms (we explicitly flag these in the language-specific READMEs), production users should route through this model with the appropriate `language=` hint:
-
-```python
-from transformers import WhisperForConditionalGeneration, WhisperProcessor
-processor = WhisperProcessor.from_pretrained("WindyWord/listen-windy-pro-engine", subfolder="safetensors")
-model = WhisperForConditionalGeneration.from_pretrained("WindyWord/listen-windy-pro-engine", subfolder="safetensors")
-
-# ig (Igbo), mn (Mongolian), or any thin-coverage language:
-ids = model.generate(input_features, language="ig", task="transcribe")
-```
-
-Languages currently flagged for this fallback:
-- **Igbo (ig)** — community ASR thin; only available fine-tune is whisper-tiny which is 39M params.
-- **Mongolian (mn)** — both predecessor and upgrade attempts have audited at ~100% WER on FLEURS.
-- **Hebrew (he)**, **Malayalam (ml)** — current language-specific models are MARGINAL; whisper-large-v3 may give better real-world results.
+**Multilingual speech-to-text engine. Transcribes audio in 100+ languages, with English as the primary trained domain.**
 
 ## Profile
 
 - **Architecture:** 1.55B params · whisper-large-v3
 - **Profile:** premium / max accuracy
 - **Base model:** [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3)
-- **Multilingual:** 99 languages directly supported; auto-detects language by default
 
 ## Variants in this repo
 
@@ -63,6 +43,7 @@ model = WhisperForConditionalGeneration.from_pretrained("WindyWord/listen-windy-
 For CPU inference via CTranslate2:
 ```python
 import ctranslate2
+# After downloading the ct2-int8 subfolder:
 model = ctranslate2.models.Whisper("path/to/ct2-int8/")
 ```
 
@@ -74,6 +55,6 @@ Part of the [WindyWord.ai](https://windyword.ai) STT fleet. Visit windyword.ai f
 
 ## Provenance & License
 
-Weights derived from [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) under Apache-2.0 (inherited). Proprietary fine-tuning by WindyWord.ai team via LoRA fog-of-mirror methodology where applicable.
+Weights derived from [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) under Apache-2.0 (inherited). Voice tiers are direct redistributions of the upstream community Whisper / distil-whisper variants; no LoRA fine-tuning has been applied to these voice models.
 
 *Certified by Opus 4.6 Opus-Claw (Dr. C) on Veron-1 (RTX 5090, Mt Pleasant SC).*