Update WER table from new test-clean sweep (transcribe.cpp 4d2270e)

README.md

@@ -132,12 +132,12 @@ OpenAI Whisper tiny — converted to GGUF for transcribe.cpp. Multilingual trans
 
 | Quantization | Download | Size | WER (LibriSpeech test-clean) |
 | --- | --- | ---: | ---: |
-| F32 | [whisper-tiny-F32.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-F32.gguf) | 146 MB | 7.49% |
-| F16 | [whisper-tiny-F16.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-F16.gguf) | 76 MB | 7.48% |
-| Q8_0 | [whisper-tiny-Q8_0.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-Q8_0.gguf) | 44 MB | 7.52% |
-| Q6_K | [whisper-tiny-Q6_K.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-Q6_K.gguf) | 43 MB | 7.54% |
-| Q5_K_M | [whisper-tiny-Q5_K_M.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-Q5_K_M.gguf) | 42 MB | 7.82% |
-| Q4_K_M | [whisper-tiny-Q4_K_M.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-Q4_K_M.gguf) | 42 MB | 7.78% |
+| F32 | [whisper-tiny-F32.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-F32.gguf) | 146 MB | 7.54% |
+| F16 | [whisper-tiny-F16.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-F16.gguf) | 76 MB | 7.49% |
+| Q8_0 | [whisper-tiny-Q8_0.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-Q8_0.gguf) | 44 MB | 7.53% |
+| Q6_K | [whisper-tiny-Q6_K.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-Q6_K.gguf) | 43 MB | 7.63% |
+| Q5_K_M | [whisper-tiny-Q5_K_M.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-Q5_K_M.gguf) | 42 MB | 7.63% |
+| Q4_K_M | [whisper-tiny-Q4_K_M.gguf](https://huggingface.co/handy-computer/whisper-tiny-gguf/resolve/main/whisper-tiny-Q4_K_M.gguf) | 42 MB | 7.76% |
 
 WER measured on the full LibriSpeech test-clean split (2620 utterances) with the transcribe.cpp default decode (greedy, suppress_tokens, temperature fallback, segment timestamps enabled). OpenAI's self-reported number on the same split is 7.54%. We don't know upstream's exact eval config, but the most likely cause of any divergence is that OpenAI's `model.generate()` defaults to `<|notimestamps|>` while transcribe.cpp's pipeline runs with timestamps enabled.