Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature/vid 592 live translation #806

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Feature/vid 592 live translation #806

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d0b25c0
Changed the pipeline to use AzureSTTService and using Dutch to Englis…
apoorv-revelmoments Dec 9, 2024
b5c7a0d
Merge branch 'pipecat-ai:main' into feature/VID-592-live-translation
apoorv-revelmoments Dec 9, 2024
eccece9
Update bot.py
apoorv-revelmoments Dec 9, 2024
b867bb3
Removed Debug print statement for stt
apoorv-revelmoments Dec 10, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 25 additions & 9 deletions examples/translation-chatbot/bot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
from pipecat.processors.aggregators.llm_response import LLMFullResponseAggregator
from pipecat.processors.aggregators.sentence import SentenceAggregator
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.azure import AzureTTSService
from pipecat.services.azure import AzureTTSService, AzureSTTService, language_to_azure_language
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import (
DailyParams,
Expand Down Expand Up @@ -46,9 +46,10 @@
# We need to use a custom service here to yield LLM frames without saving
# any context
class TranslationProcessor(FrameProcessor):
def __init__(self, language):
def __init__(self, source_language, language):
super().__init__()
self._language = language
self._source_language = source_language

async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
Expand All @@ -57,7 +58,8 @@ async def process_frame(self, frame: Frame, direction: FrameDirection):
context = [
{
"role": "system",
"content": f"You will be provided with a sentence in English, and your task is to translate it into {self._language}.",
"content": f"You will be provided with a sentence in {self._source_language}, and your task is to only ßtranslate it into {self._language}.",
#"content": f"Translate the sentence from {self._source_language} into {self._language}.",
},
{"role": "user", "content": frame.text},
]
Expand Down Expand Up @@ -97,25 +99,39 @@ async def main():
"Translator",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
transcription_settings=DailyTranscriptionSettings(extra={"interim_results": False}),
# transcription_enabled=True,
# transcription_settings=DailyTranscriptionSettings(extra={"interim_results": False}),
),
)

stt = AzureSTTService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"),
#language="ko-KR" #azure language code
language="nl-NL" #azure language code
#language="en-US" #azure language code

)
#print("Debug: STT=", stt)

tts = AzureTTSService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"),
voice="es-ES-AlvaroNeural",
#voice="es-ES-AlvaroNeural",
voice="en-US-AndrewMultilingualNeural"
#voice="nl-NL-MaartenNeural"
)

llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

sa = SentenceAggregator()
tp = TranslationProcessor("Spanish")
#tp = TranslationProcessor("Spanish")
tp = TranslationProcessor(source_language="Dutch", language="English") # LLM Prompt
lfra = LLMFullResponseAggregator()
ts = TranslationSubtitles("spanish")
ts = TranslationSubtitles("dutch")

pipeline = Pipeline([transport.input(), sa, tp, llm, lfra, ts, tts, transport.output()])
# pipeline = Pipeline([transport.input(), sa, tp, llm, lfra, ts, tts, transport.output()])
pipeline = Pipeline([transport.input(), stt, tp, llm, ts, tts, transport.output()])

task = PipelineTask(pipeline)

Expand Down