Record-setting accuracy and performance for Mandarin English transcriptions.
NVIDIA Parakeet‑CTC‑0.6B‑Unified is a 600M‑parameter ASR model trained on more than 17K hours of Mandarin Chinese (zh‑CN) and American English (en‑US) speech. It delivers high‑quality transcription for both languages, producing mixed‑case text with support for periods, commas, question marks, spaces, and apostrophes. This model is suitable for commercial deployment in production applications.
GOVERNING TERMS: The use of this model is governed by the NVIDIA Community Model License (found at https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/).
[1] Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition
[2] Fast-Conformer-CTC Model
[3] Conformer: Convolution-augmented Transformer for Speech Recognition
Architecture Type: Parakeet-CTC (also known as FastConformer-CTC) [1], [2] which is an optimized version of Conformer model [3] with 8x depthwise-separable convolutional downsampling with CTC loss
Network Architecture: Parakeet-CTC-XL-0.6B
Input Type(s): Audio
Input Format(s): wav
Input Parameters: 1-Dimension
Other Properties Related to Input: Maximum Length in seconds specific to GPU Memory, No Pre-Processing Needed, Mono channel is required.
Output Type(s): Text
Output Format: String (in Mandarin and English)
Output Parameters: 1-Dimension
Other Properties Related to Output: No Maximum Character Length, Does not handle special characters.
Supported Operating System(s):
Parakeet-CTC-XL-unified-0.6b_spe7k_zh-CN_3.0
Data Collection Method by dataset
Labeling Method by dataset
Properties:
This model is trained on over 17,000 hours of Mandarin (zh-CN) and English (en-US) speech, comprised of a dynamic blend of public and internal proprietary datasets normalized to have upper-cased, lower-cased, punctuated, and spoken forms in text.
Data Collection Method by dataset
Labeling Method by dataset
Properties:
A dynamic blend of public and internal proprietary datasets normalized to have upper-cased, lower-cased, punctuated, and spoken forms in text.
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.