# Online/streaming speech recognition

**URL:** <https://discuss.huggingface.co/t/online-streaming-speech-recognition/4456>\
**Category:** Research\
**Created:** [March 17, 2021, 12:22am UTC](https://discuss.huggingface.co/t/online-streaming-speech-recognition/4456 "2021-03-17T00:22:36Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![arkadyark](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/arkadyark/32/3421_2.png) [@arkadyark](https://discuss.huggingface.co/u/arkadyark)\
**Post date:** [March 17, 2021, 12:22am UTC](https://discuss.huggingface.co/t/online-streaming-speech-recognition/4456/1 "2021-03-17T00:22:36Z")

</div>

Are there plans to implement online decoding for the speech recognition models such as wav2vec2 and XLSR? More specifically, to be able to receive audio in short chunks, and output partial transcripts as they become available.

## Motivation

Many use cases are covered by the current wav2vec2 model in the library, involving batch recognition of pre-recorded text. However for an online application that wanted to continuously recognize speech on a live input stream, this may not be sufficient.

---

<div class="post-metadata">

**Author:** ![randy912](https://avatars.discourse-cdn.com/v4/letter/r/45deac/32.png) [@randy912](https://discuss.huggingface.co/u/randy912)\
**Post date:** [September 11, 2021, 6:50pm UTC](https://discuss.huggingface.co/t/online-streaming-speech-recognition/4456/2 "2021-09-11T18:50:39Z")

</div>

I would very much like to know whether this is possible too! Have you gotten any further on this, @arkadyark?

---

<div class="post-metadata">

**Author:** ![Salama1429](https://avatars.discourse-cdn.com/v4/letter/s/3be4f8/32.png) [@Salama1429](https://discuss.huggingface.co/u/Salama1429)\
**Post date:** [October 26, 2022, 8:19am UTC](https://discuss.huggingface.co/t/online-streaming-speech-recognition/4456/3 "2022-10-26T08:19:28Z")

</div>

please check this one

> [@Use wav2vec2 models with a microphone easily](https://discuss.huggingface.co/t/use-wav2vec2-models-with-a-microphone-easily/5522):
>
> Hello folks, I wrote a little lib to be able to use any wav2vec2 model from the model hub with a microphone. Since wav2vec2 does not support streaming mode, I used voice activity detection to create audio chunks that I can feed into the model. Here is a little example, you can [find the code on github](https://github.com/oliverguhr/wav2vec2-live). from live\_asr import LiveWav2Vec2 german\_model = "maxidl/wav2vec2-large-xlsr-german" asr = LiveWav2Vec2(german\_model,device\_name="default") asr.start() try: while True: tex…