# FastConformer architecture
Parakeet Tdt 0.6b V2
MLX format automatic speech recognition model converted from NVIDIA Parakeet TDT 0.6B v2, supporting efficient speech-to-text tasks.
Speech Recognition
P
mlx-community
24.49k
13
Stt Uz Fastconformer Hybrid Large Pc
This is a large-scale Uzbek speech recognition model based on the FastConformer architecture, supporting both Transducer and CTC decoding, and demonstrating excellent performance across multiple test sets.
Speech Recognition Other
S
nvidia
96
6
Parakeet Tdt Ctc 0.6b Ja
Parakeet TDT-CTC 0.6B is an automatic speech recognition (ASR) model capable of transcribing Japanese speech with punctuation, developed by the NVIDIA NeMo team.
Speech Recognition Japanese
P
nvidia
4,184
22
Canary 1b
Canary-1B is a multilingual multi-task model developed by NVIDIA NeMo, supporting automatic speech recognition and speech translation tasks in English, German, French, and Spanish.
Speech Recognition Supports Multiple Languages
C
nvidia
7,734
421
Parakeet Ctc 1.1b
Parakeet CTC 1.1B is an automatic speech recognition model jointly developed by NVIDIA NeMo and Suno.ai, based on the FastConformer architecture with approximately 1.1 billion parameters, supporting English speech transcription.
Speech Recognition English
P
nvidia
14.78k
29
Parakeet Rnnt 1.1b
Parakeet RNNT 1.1B is an automatic speech recognition model jointly developed by NVIDIA NeMo and Suno.ai, based on the FastConformer Transducer architecture with approximately 1.1 billion parameters, supporting English speech transcription.
Speech Recognition English
P
nvidia
13.18k
124
Stt En Fastconformer Transducer Xlarge
The NVIDIA FastConformer-Transducer is a high-performance model for English automatic speech recognition (ASR), utilizing an optimized FastConformer architecture and Transducer decoder with approximately 618 million parameters.
Speech Recognition English
S
nvidia
106
24
Stt En Fastconformer Ctc Xlarge
NVIDIA FastConformer-CTC XLarge is an Automatic Speech Recognition (ASR) model with approximately 600 million parameters, designed specifically for English speech transcription and trained using the FastConformer architecture and CTC loss.
Speech Recognition English
S
nvidia
216
2
Stt En Fastconformer Ctc Large
This is a large automatic speech recognition (ASR) model based on the FastConformer architecture, specifically designed for transcribing English speech into text.
Speech Recognition English
S
nvidia
1,001
12
Stt En Fastconformer Transducer Large
This is a large automatic speech recognition (ASR) model based on the FastConformer architecture, specifically designed for transcribing English speech into text.
Speech Recognition English
S
nvidia
1,398
7
Stt Ru Fastconformer Hybrid Large Pc
This is a FastConformer hybrid model for Russian automatic speech recognition, combining Transducer and CTC decoders with approximately 115 million parameters.
Speech Recognition Other
S
nvidia
6,513
10
Stt Be Fastconformer Hybrid Large Pc
This is a large-scale Belarusian automatic speech recognition model based on the FastConformer architecture, combining Transformer and CTC decoder loss, trained on 1,500 hours of Belarusian speech data.
Speech Recognition Other
S
nvidia
33
4
Stt Ua Fastconformer Hybrid Large Pc
NVIDIA FastConformer-Hybrid Large (ua) is a hybrid model for Ukrainian speech recognition, which combines the training of two loss functions, Transducer and CTC, with approximately 115 million parameters.
Speech Recognition
S
nvidia
381
4
Featured Recommended AI Models