- 6
- 1 443
ConvAI_RG
เข้าร่วมเมื่อ 3 พ.ย. 2024
Conversational AI Reading Group
"Foundational Speech Models and Their Efficient Training with NVIDIA NeMo" - ConvAI Talk 6
Talk 6 of the Conversational AI Reading Group about a paper entitled "Foundational Speech Models and Their Efficient Training with NVIDIA NeMo" by Piotr Żelasko.
For further information about the Reading Group, please check out poonehmousavi.github.io/rg
For further information about the Reading Group, please check out poonehmousavi.github.io/rg
มุมมอง: 501
วีดีโอ
Improving Universal Access To Modern Speech Technology
มุมมอง 12417 วันที่ผ่านมา
Talk 5 of the Conversational AI Reading Group about "Improving Universal Access To Modern Speech Technology" by Martijn Bartelds. For further information about the Reading Group, please check out poonehmousavi.github.io/rg
"Neural Audio Codecs in the Era of Speech LMs" by Haibin Wu - ConvAI Talk 4
มุมมอง 34124 วันที่ผ่านมา
Talk 4 of the Conversational AI Reading Group about "Neural Audio Codecs in the Era of Speech LMs" by Haibin Wu. For further information about the Reading Group, please check out poonehmousavi.github.io/rg
"Discrete Audio Tokens for Multimodal LLMs" - ConvAI Talk 3
มุมมอง 264หลายเดือนก่อน
Talk 3 of the Conversational AI Reading Group about "Discrete Audio Tokens for Multimodal LLMs" by Mirco Ravanelli. For further information about the Reading Group, please check out poonehmousavi.github.io/rg
"Posthoc Explanations for Audio Models" - ConvAI Talk 2
มุมมอง 116หลายเดือนก่อน
Talk 2 of the Conversational AI Reading Group about "Posthoc Explanations for Audio Models" by Cem Subakan. For further information about the Reading Group, please check out poonehmousavi.github.io/rg
"Parameter averaging is all you need to prevent forgetting" - ConvAI Talk 1
มุมมอง 1152 หลายเดือนก่อน
Talk 1 of the Conversational AI Reading Group about a paper entitled "Parameter averaging is all you need to prevent forgetting" by Peter Plantinga. For further information about the Reading Group, please check out poonehmousavi.github.io/rg
thank you for the video! it would be very interesting to evaluate wavtokenizer by this benchmark
We are expanding our benchmark to cover more tasks and tokenizers including wavtokenizer, we will release the new code and result soon.