Skip to main content

Local translation module based on the hugging face transformer

Project description

retico-hftranslate

Local translation module based on the hugging face transformer library.

Example

from retico_core import *
import retico_wav2vecasr
import retico_speechbraintts
import retico_hftranslate

msg = []


def callback(update_msg):
    global msg
    for x, ut in update_msg:
        if ut == UpdateType.ADD:
            msg.append(x)
        if ut == UpdateType.REVOKE:
            msg.remove(x)
    txt = ""
    committed = False
    for x in msg:
        txt += x.text + " "
        committed = committed or x.committed
    print(" " * 80, end="\r")
    print(f"{txt}", end="\r")
    if committed:
        msg = []
        print("")


m1 = audio.MicrophoneModule()
m2 = retico_wav2vecasr.Wav2VecASRModule(language="de")
m3 = retico_hftranslate.HFTranslateModule(from_lang="de", to_lang="en")
m5 = retico_speechbraintts.SpeechBrainTTSModule(language="en")
m6 = audio.SpeakerModule(rate=22050)
m4 = debug.CallbackModule(callback)

m1.subscribe(m2)
m2.subscribe(m3)
m3.subscribe(m4)
m3.subscribe(m5)
m5.subscribe(m6)

network.run(m1)

print("Press any key to exit")
input()

network.stop(m1)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

retico-hftranslate-0.1.2.tar.gz (7.2 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page