Record-setting accuracy and performance for English transcription.
Parakeet is a major step forward in the evolution of conversational AI. Its exceptional accuracy, coupled with the flexibility and ease of use offered by NeMo, empowers developers to create more natural and intuitive voice-powered applications. The possibilities are endless, from enhancing the accuracy of virtual assistants to enabling seamless real-time communication.
Parakeet transcribes audio into text, using spaces and apostrophes where needed
GOVERNING TERMS: Use of this model is governed by the NVIDIA Community Model License Agreement.
AI models generate responses and outputs based on complex algorithms and machine learning techniques, and those responses or outputs may be inaccurate or indecent. By testing this model, you assume the risk of any harm caused by any response or output of the model. Please do not upload any confidential information or personal data. Your use is logged for security.
Architecture Type: Convolutional Neural Network + Transformer
Network Architecture: Fast Conformer Encoder with CTC Decoder
Input Type(s): Audio in English
Input Format(s): Linear PCM 16-bit 1 channel
Output Type(s): Text String in English with Timestamps
Runtime Engine(s):
Supported Operating System(s):
Parakeet-1.1b-ctc-en-us-asr-set-6.0
Engine: Triton
Test Hardware:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards. Please report security vulnerabilities or NVIDIA AI Concerns here.