diff --git a/README.md b/README.md index 16d3a23..e3a7a27 100644 --- a/README.md +++ b/README.md @@ -3,14 +3,12 @@ Whisper realtime streaming for long speech-to-text transcription and translation **Turning Whisper into Real-Time Transcription System** -Demonstration paper, by Dominik Macháček, Raj Dabre, Ondřej Bojar, 2023 +Demonstration paper, by [Dominik Macháček](https://ufal.mff.cuni.cz/dominik-machacek), [Raj Dabre](https://prajdabre.github.io/), [Ondřej Bojar](https://ufal.mff.cuni.cz/ondrej-bojar), 2023 -Abstract: Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription. In this paper, we build on top of Whisper and create Whisper-Streaming, an implementation of real-time speech transcription and translation of Whisper-like models. Whisper-Streaming uses local agreement policy with self-adaptive latency to enable streaming transcription. We show that Whisper-Streaming achieves high quality and 3.3 seconds latency on unsegmented long-form speech transcription test set, and we demonstrate its robustness and practical usability as a component in live transcription service at a multilingual conference. +Abstract: Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real-time transcription. In this paper, we build on top of Whisper and create Whisper-Streaming, an implementation of real-time speech transcription and translation of Whisper-like models. Whisper-Streaming uses local agreement policy with self-adaptive latency to enable streaming transcription. We show that Whisper-Streaming achieves high quality and 3.3 seconds latency on unsegmented long-form speech transcription test set, and we demonstrate its robustness and practical usability as a component in live transcription service at a multilingual conference. -Paper in proceedings: http://www.afnlp.org/conferences/ijcnlp2023/proceedings/main-demo/cdrom/pdf/2023.ijcnlp-demo.3.pdf - -Demo video: https://player.vimeo.com/video/840442741 +[Paper PDF](https://aclanthology.org/2023.ijcnlp-demo.3.pdf), [Demo video](https://player.vimeo.com/video/840442741) [Slides](http://ufallab.ms.mff.cuni.cz/~machacek/pre-prints/AACL23-2.11.2023-Turning-Whisper-oral.pdf) -- 15 minutes oral presentation at IJCNLP-AACL 2023 @@ -157,7 +155,7 @@ The code whisper_online.py is nicely commented, read it as the full documentatio This pseudocode describes the interface that we suggest for your implementation. You can implement any features that you need for your application. -``` +```python from whisper_online import * src_lan = "en" # source language @@ -185,7 +183,7 @@ online.init() # refresh if you're going to re-use the object for the next audio ### Server -- real-time from mic -`whisper_online_server.py` has the same model options as `whisper_online.py`, plus `--host` and `--port` of the TCP connection. See help message (`-h` option). +`whisper_online_server.py` has the same model options as `whisper_online.py`, plus `--host` and `--port` of the TCP connection and the `--warmup-file`. See the help message (`-h` option). Client example: @@ -226,12 +224,20 @@ In more detail: we use the init prompt, we handle the inaccurate timestamps, we re-process confirmed sentence prefixes and skip them, making sure they don't overlap, and we limit the processing buffer window. -Contributions are welcome. - ### Performance evaluation [See the paper.](http://www.afnlp.org/conferences/ijcnlp2023/proceedings/main-demo/cdrom/pdf/2023.ijcnlp-demo.3.pdf) +### Contributions + +Contributions are welcome. We acknowledge especially: + +- [The GitHub contributors](https://github.com/ufal/whisper_streaming/graphs/contributors) for their pull requests with new features and bugfixes. +- [The translation of this repo into Chinese.](https://github.com/Gloridust/whisper_streaming_CN) +- [Ondřej Plátek](https://opla.cz/) for the paper pre-review. +- [Peter Polák](https://ufal.mff.cuni.cz/peter-polak) for the original idea. +- The UEDIN team of the [ELITR project](https://elitr.eu) for the original line_packet.py. + ## Contact diff --git a/whisper_online.py b/whisper_online.py index c4a90e3..651ceb4 100644 --- a/whisper_online.py +++ b/whisper_online.py @@ -626,7 +626,7 @@ if __name__ == "__main__": # load the audio into the LRU cache before we start the timer a = load_audio_chunk(audio_path,0,1) - # warm up the ASR, because the very first transcribe takes much more time than the other + # warm up the ASR because the very first transcribe takes much more time than the other asr.transcribe(a) beg = args.start_at diff --git a/whisper_online_server.py b/whisper_online_server.py index 188038a..f652a75 100644 --- a/whisper_online_server.py +++ b/whisper_online_server.py @@ -10,6 +10,8 @@ parser = argparse.ArgumentParser() # server options parser.add_argument("--host", type=str, default='localhost') parser.add_argument("--port", type=int, default=43007) +parser.add_argument("--warmup-file", type=str, dest="warmup_file", + help="The path to a speech audio wav file to warm up Whisper so that the very first chunk processing is fast. It can be e.g. https://github.com/ggerganov/whisper.cpp/raw/master/samples/jfk.wav .") # options from whisper_online @@ -26,18 +28,25 @@ language = args.lan asr, online = asr_factory(args) min_chunk = args.min_chunk_size -demo_audio_path = "cs-maji-2.16k.wav" -if os.path.exists(demo_audio_path): - # load the audio into the LRU cache before we start the timer - a = load_audio_chunk(demo_audio_path,0,1) - # TODO: it should be tested whether it's meaningful - # warm up the ASR, because the very first transcribe takes much more time than the other - asr.transcribe(a) +if args.buffer_trimming == "sentence": + tokenizer = create_tokenizer(tgt_language) else: - print("Whisper is not warmed up",file=sys.stderr) - + tokenizer = None +online = OnlineASRProcessor(asr,tokenizer,buffer_trimming=(args.buffer_trimming, args.buffer_trimming_sec)) +# warm up the ASR because the very first transcribe takes more time than the others. +# Test results in https://github.com/ufal/whisper_streaming/pull/81 +msg = "Whisper is not warmed up. The first chunk processing may take longer." +if args.warmup_file: + if os.path.isfile(args.warmup_file): + a = load_audio_chunk(args.warmup_file,0,1) + asr.transcribe(a) + print("INFO: Whisper is warmed up.",file=sys.stderr) + else: + print("WARNING: The warm up file is not available. "+msg,file=sys.stderr) +else: + print("WARNING: " + msg, file=sys.stderr) ######### Server objects