v1.12.19

What's Changed

• Fix building without TTS for C API by @csukuangfj in #2838
• [ZipVoice] Fix english tokenization error by @pkufool in #2834
• Add simulate streaming ASR Python example for Paraformer by @csukuangfj in #2839
• Fix building JNI for Windows. by @csukuangfj in #2840
• Avoid NaN in NeMo speaker embedding models. by @csukuangfj in #2844
• add spacemit ort ep for spacemit riscv cpus by @alex-spacemit in #2837
• Add token-level confidence scores (ys_probs) for offline transducer models by @Mahmoud-ghareeb in #2843
• Fix token log probabilities in offline transducer modified beam search decoder by @Mahmoud-ghareeb in #2846
• Support AXERA ax630, ax650, and axcl backends. by @Abandon-ht in #2849
• Refactor axera npu examples by @csukuangfj in #2850
• fix matcha tts zh-en model by @csukuangfj in #2851
• Fix the English part for Matcha TTS. by @csukuangfj in #2853
• Refactor text-utils by @csukuangfj in #2855
• Fix matcha tts by @csukuangfj in #2856
• Add a space between English words for Matcha zh-en TTS by @csukuangfj in #2858
• Fix punctuations in matcha zh-en tts by @csukuangfj in #2859
• Upload matcha tts zh-en model by @csukuangfj in #2865
• Fix the discrepancy with the Silero VAD isSpeech logic by @ming030890 in #2863
• Release v1.12.19 by @csukuangfj in #2868

New Contributors

• @alex-spacemit made their first contribution in #2837
• @Mahmoud-ghareeb made their first contribution in #2843
• @Abandon-ht made their first contribution in #2849
• @ming030890 made their first contribution in #2863

Full Changelog: v1.12.18...v1.12.19