thangpnb
thangpnb
Thank you for your prompt response. However, in the example of the JSONL file format here: (https://github.com/X-LANCE/SLAM-LLM/blob/main/examples/s2s/demo/demo_data/jsonl_demo-en.jsonl) It seems that, if I am using **jsonl** format, the value of **answer_snac**...
Thank you for your clear explanation.
@cwx-worst-one can I train SLAM-Omni with 1 Gtx 3090 24GB
Could you please tell me the main difference between `finetune_s2s.sh` and `finetune_s2s_group.sh` script?
thank you for your info
If I want to train with a custom dataset in Korean or Vietnamese, are there any considerations I should keep in mind when using Whisper and CosyVoice, since they don't...
I have trained whisper small model on vietnamese and korean. I think it will be better if train cosyvoice on vietnamese and korean to get tokens.
@cwx-worst-one: Have you tested the reproduction Mini-Omni version with SNAC yet? How does its speed and response quality compare to SLAM-Omni version?
I think Mini-Omni version with code_type=SNAC will be much faster than SLAM-Omni version with code_type=Cosyvoice. Is that true?
Can you provide pretrained model for Mini-Omni streaming inference ``` # Single-turn streaming bash ./examples/s2s/scripts/inference/mini-omni/inference_s2s_online_stream.sh```