quantize : fix load vocab crash when len is 128 (#1160)

* quantize : fix load vocab crash when len is 128

* ci : add quantize job

.github/workflows/build.yml

@@ -426,6 +426,19 @@ jobs:
           name: whispercpp.jar
           path: bindings/java/build/libs/whispercpp-*.jar
 
+  quantize:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Clone
+        uses: actions/checkout@v3
+
+      - name: Test quantize
+        run: |
+          ./models/download-ggml-model.sh tiny.en
+          make quantize
+          ./quantize models/ggml-tiny.en.bin models/ggml-tiny.en-q4_0.bin q4_0
+
 #      - name: Publish package
 #        if: ${{ github.ref == 'refs/heads/master' }}
 #        uses: gradle/gradle-build-action@v2

examples/quantize/quantize.cpp

@@ -138,7 +138,7 @@ bool whisper_model_quantize(const std::string & fname_inp, const std::string & f
         //    return false;
         //}
 
-        char word[128];
+        char word[129];
 
         for (int i = 0; i < n_vocab; i++) {
             uint32_t len;