-
Hello folks I used nvidia quartznet for asr and it is taking wav files to transcribe. How to do real time streaming asr model Thanks |
Beta Was this translation helpful? Give feedback.
Replies: 10 comments
-
How to do real time streaming using Citrinet asr model? Will it be the same way as of Quartznet? |
Beta Was this translation helpful? Give feedback.
-
do you know how to implement quartznet for real time streaming?? |
Beta Was this translation helpful? Give feedback.
-
No, I didn't try yet by myself. |
Beta Was this translation helpful? Give feedback.
-
For streaming you need FrameAsr like from this notebook https://github.com/NVIDIA/NeMo/blob/main/tutorials/asr/02_Online_ASR_Microphone_Demo.ipynb or use Nvidia Jarvis |
Beta Was this translation helpful? Give feedback.
-
Yes, I tried this earlier but it didn't work for CitriNet model. |
Beta Was this translation helpful? Give feedback.
-
What you mean by didn't work? Did you use correct stats? #1203 |
Beta Was this translation helpful? Give feedback.
-
Correct, It is working for Quartznet model, but no output was coming for Citrinet model. I wanted to know what could be the reason of it. @khursani8 thanx for your response, I'll be checking for different stride. |
Beta Was this translation helpful? Give feedback.
-
We are working on adding streaming ASR tutorial. @jbalam-nv fyi. |
Beta Was this translation helpful? Give feedback.
-
@snaaz21 were you able to run Citrinet model for asr (with microphone)? Can you guide a bit, would be huge help. |
Beta Was this translation helpful? Give feedback.
-
Streaming tutorial that should work with Both Conformer-CTC and Citrinet are now in NeMo: https://github.com/NVIDIA/NeMo/blob/main/tutorials/asr/Streaming_ASR.ipynb This is also available as a script for offline long form audio decoding: https://github.com/NVIDIA/NeMo/blob/main/examples/asr/speech_to_text_buffered_infer.py |
Beta Was this translation helpful? Give feedback.
For streaming you need FrameAsr like from this notebook https://github.com/NVIDIA/NeMo/blob/main/tutorials/asr/02_Online_ASR_Microphone_Demo.ipynb or use Nvidia Jarvis