almost 3 years ago
Bengaluru, IndiaSenior
Responsibilities
- Develop speech-to-text pipelines for transcription, diarization, and voice activity detection.
- Train, deploy, and maintain scalable automatic speech recognition pipelines for the ASR engine.
- Research state-of-the-art speech recognition techniques and share knowledge with colleagues.
- Conduct experiments with model architectures, training schemes, and approaches from ASR literature.
- Collaborate on system architecture and design.
- Develop algorithms and models for large-scale applications and deliver products in an agile environment.
Requirements
- At least 2 years of experience and a bachelor's degree in Computer Science or a related field from a tier-1 engineering institute.
- Experience deploying deep learning-based models for speech recognition pipelines.
- Awareness of state-of-the-art research in speech recognition and signal processing.
- Experience with algorithm and model development for large-scale applications.
- Strong knowledge of machine learning fundamentals.
- Experience with Python and PyTorch.
Categories
