deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 17:39:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: generate token2wav_request_id from cosyvoice2

Browse Source 
- Since all token2wav requests within a single cosyvoice2 request must share the same request_id, modify the logic so that a new request_id is generated only if it does not already exist, and ensure that the same request_id is sent consistently.
This commit is contained in:
김의진
2025-10-27 18:12:17 +09:00
parent fa2781405f
commit e8bf717333
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
runtime/triton_trtllm/model_repo/cosyvoice2/1/model.py
View File

@@ -28,6 +28,7 @@ import json
import os import os
import threading import threading
import time import time
from uuid import uuid4
import numpy as np import numpy as np
import torch import torch
@@ -364,6 +365,7 @@ class TritonPythonModel:
# Generate semantic tokens with LLM # Generate semantic tokens with LLM
generated_ids_iter = self.forward_llm(input_ids) generated_ids_iter = self.forward_llm(input_ids)
token2wav_request_id = request_id or str(uuid4())
if self.decoupled: if self.decoupled:
response_sender = request.get_response_sender() response_sender = request.get_response_sender()
@@ -392,7 +394,7 @@ class TritonPythonModel:
this_tts_speech_token = torch.tensor(this_tts_speech_token).unsqueeze(dim=0).to(torch.int32).to(self.device) this_tts_speech_token = torch.tensor(this_tts_speech_token).unsqueeze(dim=0).to(torch.int32).to(self.device)
sub_tts_speech = self.forward_token2wav( sub_tts_speech = self.forward_token2wav(
this_tts_speech_token, request_id, prompt_speech_tokens, this_tts_speech_token, token2wav_request_id, prompt_speech_tokens,
prompt_speech_feat, prompt_spk_embedding, token_offset, False prompt_speech_feat, prompt_spk_embedding, token_offset, False
) )
@@ -427,7 +429,7 @@ class TritonPythonModel:
time.sleep(0.02) time.sleep(0.02)
this_tts_speech_token = torch.tensor(semantic_token_ids_arr).unsqueeze(dim=0).to(torch.int32).to(self.device) this_tts_speech_token = torch.tensor(semantic_token_ids_arr).unsqueeze(dim=0).to(torch.int32).to(self.device)
sub_tts_speech = self.forward_token2wav(this_tts_speech_token, request_id, prompt_speech_tokens, prompt_speech_feat, prompt_spk_embedding, token_offset, True) sub_tts_speech = self.forward_token2wav(this_tts_speech_token, token2wav_request_id, prompt_speech_tokens, prompt_speech_feat, prompt_spk_embedding, token_offset, True)
audio_tensor = pb_utils.Tensor.from_dlpack("waveform", to_dlpack(sub_tts_speech)) audio_tensor = pb_utils.Tensor.from_dlpack("waveform", to_dlpack(sub_tts_speech))
inference_response = pb_utils.InferenceResponse(output_tensors=[audio_tensor]) inference_response = pb_utils.InferenceResponse(output_tensors=[audio_tensor])
response_sender.send(inference_response) response_sender.send(inference_response)
@@ -441,7 +443,7 @@ class TritonPythonModel:
if generated_ids is None or len(generated_ids) == 0: if generated_ids is None or len(generated_ids) == 0:
raise pb_utils.TritonModelException("Generated IDs is None or empty") raise pb_utils.TritonModelException("Generated IDs is None or empty")
audio = self.forward_token2wav(generated_ids, request_id, prompt_speech_tokens, prompt_speech_feat, prompt_spk_embedding) audio = self.forward_token2wav(generated_ids, token2wav_request_id, prompt_speech_tokens, prompt_speech_feat, prompt_spk_embedding)
# Prepare response # Prepare response
audio_tensor = pb_utils.Tensor.from_dlpack("waveform", to_dlpack(audio)) audio_tensor = pb_utils.Tensor.from_dlpack("waveform", to_dlpack(audio))