💎 ASR improvements
Our newest generation of ASR models using conformer transducer architecture are now in public beta for all users. The new architecture provides significant accuracy gains in word error rate.
We use cookies to analyze our website traffic and performance. By clicking “Accept”, you agree Speechly can store cookies on your device and disclose information in accordance with our Cookie Policy.
Our newest generation of ASR models using conformer transducer architecture are now in public beta for all users. The new architecture provides significant accuracy gains in word error rate.