deepgeek/gradio-webrtc
2
0
Fork 0
mirror of https://github.com/HumanAIGC-Engineering/gradio-webrtc.git synced 2026-02-05 18:09:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

Raise errors automatically (#69)

Browse Source 
* Add auto errors

* change code

---------

Co-authored-by: Freddy Boulton <freddyboulton@hf-freddy.local>
This commit is contained in:
Freddy Boulton
2025-02-24 20:21:25 -05:00
committed by GitHub
parent c36fb8da50
commit 5a4693ee0b
20 changed files with 297 additions and 344 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
demo/llm_voice_chat/app.py
View File

@@ -10,7 +10,6 @@ from fastrtc import (
AdditionalOutputs,
ReplyOnPause,
Stream,
WebRTCError,
get_stt_model,
get_twilio_turn_credentials,
)
@@ -30,42 +29,36 @@ def response(
audio: tuple[int, NDArray[np.int16 | np.float32]],
chatbot: list[dict] | None = None,
):
try:
chatbot = chatbot or []
messages = [{"role": d["role"], "content": d["content"]} for d in chatbot]
start = time.time()
text = stt_model.stt(audio)
print("transcription", time.time() - start)
print("prompt", text)
chatbot.append({"role": "user", "content": text})
yield AdditionalOutputs(chatbot)
messages.append({"role": "user", "content": text})
response_text = (
groq_client.chat.completions.create(
model="llama-3.1-8b-instant",
max_tokens=512,
messages=messages, # type: ignore
)
.choices[0]
.message.content
chatbot = chatbot or []
messages = [{"role": d["role"], "content": d["content"]} for d in chatbot]
start = time.time()
text = stt_model.stt(audio)
print("transcription", time.time() - start)
print("prompt", text)
chatbot.append({"role": "user", "content": text})
yield AdditionalOutputs(chatbot)
messages.append({"role": "user", "content": text})
response_text = (
groq_client.chat.completions.create(
model="llama-3.1-8b-instant",
max_tokens=512,
messages=messages, # type: ignore
)
.choices[0]
.message.content
)
chatbot.append({"role": "assistant", "content": response_text})
chatbot.append({"role": "assistant", "content": response_text})
for chunk in tts_client.text_to_speech.convert_as_stream(
text=response_text, # type: ignore
voice_id="JBFqnCBsd6RMkjVDRZzb",
model_id="eleven_multilingual_v2",
output_format="pcm_24000",
):
audio_array = np.frombuffer(chunk, dtype=np.int16).reshape(1, -1)
yield (24000, audio_array)
yield AdditionalOutputs(chatbot)
except Exception:
import traceback
traceback.print_exc()
raise WebRTCError(traceback.format_exc())
for chunk in tts_client.text_to_speech.convert_as_stream(
text=response_text, # type: ignore
voice_id="JBFqnCBsd6RMkjVDRZzb",
model_id="eleven_multilingual_v2",
output_format="pcm_24000",
):
audio_array = np.frombuffer(chunk, dtype=np.int16).reshape(1, -1)
yield (24000, audio_array)
yield AdditionalOutputs(chatbot)
chatbot = gr.Chatbot(type="messages")