English and Sinhala

Description and use

<h1> English and Sinhala </h1> <p>The Sinhala voice said "ආයුබෝවන්. මම හර්ත්ලන්." Inference took 112 milliseconds. The greeting itself was 2.04 seconds of audio.</p> <p>Savindu Thathsara, <a href="https://savithathsara.me" rel="noopener noreferrer">savithathsara.me</a>. This is a Hearthlen note from the laptop.</p> <p>English was the only filled-in language. Sinhala was an empty row in the same manifest. That row now points at a real voice, <code>si_LK-sinhala-medium</code>, and both languages share one multilingual speech model. The wake phrase is still "hey Hearthlen". After it, a sentence i

Problem

<h1> English and Sinhala </h1> <p>The Sinhala voice said "ආයුබෝවන්. මම හර්ත්ලන්." Inference took 112 milliseconds. The greeting itself was 2.04 seconds of audio.</p> <p>Savindu Thathsara, <a href="https://savithathsara.me" rel="noopener noreferrer">savithathsara.me</a>. This is a Hearthlen note from the laptop.</p> <p>English was the only filled-in language. Sinhala was an empty row in the same manifest. That row now points at a real voice, <code>si_LK-sinhala-medium</code>, and both languages share one multilingual speech model. The wake phrase is still "hey Hearthlen". After it, a sentence i

Outcome

<h1> English and Sinhala </h1> <p>The Sinhala voice said "ආයුබෝවන්. මම හර්ත්ලන්." Inference took 112 milliseconds. The greeting itself was 2.04 seconds of audio.</p> <p>Savindu Thathsara, <a href="https://savithathsara.me" rel="noopener noreferrer">savithathsara.me</a>. This is a Hearthlen note from the laptop.</p> <p>English was the only filled-in language. Sinhala was an empty row in the same manifest. That row now points at a real voice, <code>si_LK-sinhala-medium</code>, and both languages share one multilingual speech model. The wake phrase is still "hey Hearthlen". After it, a sentence i

Evidence

English and Sinhala

Source