Update README: q6q8 replaces broken q4q6, add WER validation table

README.md

@@ -41,11 +41,20 @@ access even with the weights already on disk.
 | `openai_whisper-base` | [`openai/whisper-base`](https://huggingface.co/openai/whisper-base) | full precision |
 | `openai_whisper-small` | [`openai/whisper-small`](https://huggingface.co/openai/whisper-small) | full precision |
 | `openai_whisper-large-v3-turbo` | [`openai/whisper-large-v3-turbo`](https://huggingface.co/openai/whisper-large-v3-turbo) | full precision, 1.63 GB |
-| `dictionlabs_whisper-large-v3-turbo-q4q6` | [`openai/whisper-large-v3-turbo`](https://huggingface.co/openai/whisper-large-v3-turbo) | compressed, 547 MB |
+| `dictionlabs_whisper-large-v3-turbo-q6q8` | [`openai/whisper-large-v3-turbo`](https://huggingface.co/openai/whisper-large-v3-turbo) | compressed, 703 MB |
 
-`dictionlabs_whisper-large-v3-turbo-q4q6` is a compressed version of the turbo model above,
-same weights, reduced precision, verified to hold up on our accuracy checks. Same quality target,
-about a third smaller.
+`dictionlabs_whisper-large-v3-turbo-q6q8` is a compressed version of the turbo model above,
+same weights, reduced precision, about half the size. Verified against the full precision
+build with real transcription tests, not just internal accuracy checks:
+
+| Language | Full precision (WER/CER) | Compressed (WER/CER) |
+|---|---|---|
+| German | 2.8% | 3.4% |
+| English | 15.5% | 15.5% |
+| French | 7.8% | 8.8% |
+| Japanese | 2.6% | 2.6% |
+| Korean | 18.1% | 22.5% |
+| Chinese | 9.0% | 9.0% |
 
 ## Licence