skzheng
skzheng
Thanks for your greate job.I have tried this project in my own computer(win10, 1060ti 3gb), and I think the similarity of voice is good.Do you have any ideas of how...
Is it a front-end come true when I finish “New-Language-Support”? What data I need to prepare is just a phoneset file and text data, isn't it?
Can wavernn training it with a noisy dataset?Why I ask this question because I have train wavenet with clean dataset and it get good result, but when I train it...
I try to wrap a audio recoder( react [mic)](https://github.com/hackingbeauty/react-mic) as a dash component, but i down know how to upload the recorded wav file, can anyone help me, thanks. Part...
As my experiment , the result of glow-tts sounds more like robot than a real person, do you have any method could make it more nature, like the result or...
GPT2 推理怎么使用beam_search,并同时输出多个结果呢?有参考代码么?谢谢!
How can i get actually note duration from midi_obj( midi_obj = miditoolkit.midi.parser.MidiFile() ), thanks? I find it's not right to get duration by codes fellow: ` notes = midi_obj.instruments[0].notes durations...
env: A40 * 4 runing script: accelerate launch --num_processes 3 --config_file configs/accelerate_configs/deepspeed_zero3.yaml scripts/run_r1_grpo.py --config receipes/grpo-qwen-2.5-3b-deepseek-r1-countdown.yaml config: # GRPO specific parameters beta: 0.001 # 0.04 as in the deepseek math paper...
env: node: 3 gpus per node: a100*8 error info: ``` ... File "/opt/conda/lib/python3.10/site-packages/colossalai/booster/booster.py", line 221, in execute_pipeline [rank23]: return self.plugin.execute_pipeline(data_iter, model, criterion, optimizer, return_loss, return_outputs) [rank23]: File "/opt/conda/lib/python3.10/site-packages/colossalai/booster/plugin/hybrid_parallel_plugin.py", line 1409,...