RNN-WER
DeepMindUniversity of TorontoSpeech recognition (ASR)
Developed by DeepMind,University of Toronto in 2014, RNN-WER is a Speech recognition (ASR) model with 26500000.0 parameters.
About RNN-WER
This paper presents a speech recognition system that directly transcribes audio data with text, without requiring an intermediate phonetic representation. The system is based on a combination of the deep bidirectional LSTM recurrent neural network ar
Details
- Provider
- DeepMind,University of Toronto
- Task
- Speech recognition (ASR)
- Parameters
- 26500000.0
- Released
- 2014-06-22