DeepSpeech2
End‑to‑end speech recognition model using CNN and bidirectional RNN layers with CTC loss.
DeepSpeech2 is an end‑to‑end automatic speech recognition (ASR) model. It uses convolutional layers for feature extraction followed by bidirectional recurrent layers and CTC for sequence‑to‑sequence learning.
Not supported
This model is currently not supported on any IoT chipset.
To see performance metrics for this model on other chipsets, click the button below.
View for other chipsetsTechnical Details
Input resolution:Spectrogram (800 frames x 161 features)
Model size:330.48MB
Number of parameters:94.6M
Applicable Scenarios
- Voice Assistants
- Transcription Services
- Accessibility
- Voice Commands
License
Model:APACHE-2.0
Tags
- foundation
- real-time
Supported IoT Devices
- Arduino VENTUNO Q
- Dragonwing IQ-8275 EVK
- Dragonwing IQ-9075 EVK
- Dragonwing Q-8750
- QCS8550 (Proxy)
Supported IoT Chipsets
- Qualcomm® Dragonwing™ IQ-8275
- Qualcomm® Dragonwing™ QCS8550 (Proxy)
- Qualcomm® Dragonwing™ Q-8750
- Qualcomm® Dragonwing™ IQ-9075
Related Models
See all models
Looking for more? See models created by industry leaders.
Discover Model Makers