Conformer-2: Advanced Speech Recognition Model with Improved Speed and Accuracy
Introducing Conformer-2, an advanced speech recognition model with improved speed, alphanumerics, proper noun recognition, and noise robustness.
00:00:00 Introducing Conformer-2, an enhanced speech recognition model with improved speed, alphanumerics, proper noun recognition, and noise robustness. It's the default model on Assembly AI's API, trained on 1.1 million hours of data for significant performance improvements.
🔍 Conformer-2 is an upgraded speech recognition model that outperforms Conformer-1 in terms of speed, recognition of alphanumerics and proper nouns, and noise robustness.
🔎 Conformer-2 is already the default model on Assembly AI's API.
📈 The size of Conformer-2 has increased to 450 million parameters and it has been trained on 1.1 million hours of data, resulting in significant performance improvements across various domains and benchmarks.
00:01:03 Conformer-2 is a state-of-the-art speech recognition model that uses noisy student-teacher training for semi-supervised learning. It optimizes latency and improves data quality with ensemble teacher models and data filtering techniques.
🔍 Conformer-2 uses noisy student teacher training to improve the training data quality and quantity.
⏱️ Optimizations on the system side reduce latency and allow scaling beyond 1 million data mark.
🧩 Conformer-2 utilizes an ensemble of teacher models and data filtering techniques to ensure high quality pseudo labels and avoid overfitting.
00:02:06 Conformer-2 is an advanced speech recognition model that focuses on alphanumerics and proper noun recognition. It emphasizes the importance of accurately transcribing proper nouns and alphanumerics, which are crucial in real-world applications.
💡 Conformer-2 is a state-of-the-art speech recognition model.
🔎 Conformer-2 focuses on alphanumerics recognition and proper noun recognition.
⚙️ The correct recognition of alphanumerics is crucial for the effectiveness of a speech recognition model.
00:03:09 Conformer-2 improves alphanumerics and proper noun recognition. Control transcription costs with the new Speech thresholds parameter. Available now for integration.
✨ Conformer-2 has improved alphanumerics and proper noun recognition compared to Conformer-1.
💰 The new parameter called Speech thresholds allows users to control the cost of transcriptions on Assembly AI.
⏱️ Conformer-2 can process files based on a specified minimum number of minutes, reducing costs for sleep podcasts, music, and empty audio files.
Want to deep dive into this video?
