# \#conversational-ai

**URL:** https://forums.developer.nvidia.com/tag/conversational-ai/234.md

[Latest](https://forums.developer.nvidia.com/latest.md) · [Categories](https://forums.developer.nvidia.com/categories.md) · [Tags](https://forums.developer.nvidia.com/tags.md)

---

## [Rtx 2080 ...not the Ti ...Does it have any cappabilities in AI models...i want to buy a jetson but i cant right now](https://forums.developer.nvidia.com/t/rtx-2080-not-the-ti-does-it-have-any-cappabilities-in-ai-models-i-want-to-buy-a-jetson-but-i-cant-right-now/194729)

<div class="topic-metadata">

**Author:** [@benoitlagace376](https://forums.developer.nvidia.com/u/benoitlagace376)\
**Replies:** 1\
**Last updated:** [November 2, 2025, 10:09am UTC](https://forums.developer.nvidia.com/t/rtx-2080-not-the-ti-does-it-have-any-cappabilities-in-ai-models-i-want-to-buy-a-jetson-but-i-cant-right-now/194729 "2025-11-02T10:09:38Z")

</div>

in term of running a model with speech input and output ? training would have to be done on cloud i suppose or very slowly local ?? this is not really easy to find the minimal requirements, i have found that for the ngc …

---

## [Seeking Guidance for Developing a Custom Generative AI-Driven Conversational UI for Electronic Devices](https://forums.developer.nvidia.com/t/seeking-guidance-for-developing-a-custom-generative-ai-driven-conversational-ui-for-electronic-devices/308222)

<div class="topic-metadata">

**Author:** [@mr.summer0900](https://forums.developer.nvidia.com/u/mr.summer0900)\
**Replies:** 3\
**Last updated:** [April 24, 2025, 3:36pm UTC](https://forums.developer.nvidia.com/t/seeking-guidance-for-developing-a-custom-generative-ai-driven-conversational-ui-for-electronic-devices/308222 "2025-04-24T15:36:04Z")

</div>

Hiya everyone and hiya to the person who’ll give a response :), I’m reaching out to seek guidance on a project I’m very interested in but have little prior practical experience with. My goal is to create a custom genera…

---

## [Request for Trial Activation and Rate Limit Increase (audio2face-3d)](https://forums.developer.nvidia.com/t/request-for-trial-activation-and-rate-limit-increase-audio2face-3d/331208)

<div class="topic-metadata">

**Author:** [@leonardo.mogianesi](https://forums.developer.nvidia.com/u/leonardo.mogianesi)\
**Replies:** 1\
**Last updated:** [April 24, 2025, 10:07am UTC](https://forums.developer.nvidia.com/t/request-for-trial-activation-and-rate-limit-increase-audio2face-3d/331208 "2025-04-24T10:07:55Z")

</div>

Hi, I requested the 90-day NVIDIA AI Enterprise trial via NGC over a week ago, but nothing has happened yet. The system still says “We’re setting up your credentials to start your no-cost, 90-day trial”, and I haven’t r…

---

## [How to Power Our Mobile AI Agent with NVIDIA Tech?](https://forums.developer.nvidia.com/t/how-to-power-our-mobile-ai-agent-with-nvidia-tech/330708)

<div class="topic-metadata">

**Author:** [@umut2](https://forums.developer.nvidia.com/u/umut2)\
**Replies:** 2\
**Last updated:** [April 22, 2025, 3:57pm UTC](https://forums.developer.nvidia.com/t/how-to-power-our-mobile-ai-agent-with-nvidia-tech/330708 "2025-04-22T15:57:40Z")

</div>

Hello everyone! We just got into the NVIDIA Inception Program, and have a big question. We’re building an AI agent for a mobile app that handles STT and TTS locally and leverages fine-tuned LLMs via APIs. We’re explorin…

---

## [Riva Speech Server Fails to Start Due to Model Loading Errors](https://forums.developer.nvidia.com/t/riva-speech-server-fails-to-start-due-to-model-loading-errors/320737)

<div class="topic-metadata">

**Author:** [@jepetolee](https://forums.developer.nvidia.com/u/jepetolee)\
**Replies:** 3\
**Last updated:** [January 27, 2025, 5:27pm UTC](https://forums.developer.nvidia.com/t/riva-speech-server-fails-to-start-due-to-model-loading-errors/320737 "2025-01-27T17:27:42Z")

</div>

I encountered several issues while running the assessment.ipynb file in the NVIDIA DLI course “Building Conversational AI Applications”, specifically during the setup and execution of Riva Speech Skills. Below are the de…

---

## [On-premise deployment of LLM solution](https://forums.developer.nvidia.com/t/on-premise-deployment-of-llm-solution/307833)

<div class="topic-metadata">

**Author:** [@jason234](https://forums.developer.nvidia.com/u/jason234)\
**Replies:** 0\
**Last updated:** [September 25, 2024, 6:12am UTC](https://forums.developer.nvidia.com/t/on-premise-deployment-of-llm-solution/307833 "2024-09-25T06:12:15Z")

</div>

Hello Everyone, We are developing an AI Assistant using the Mistral LLM(7b model). Currently the inference happens on an A40 GPU. We want to know the best practices for deploying an on-premise LLM solution using a GPU. …

---

## [Conversion from etlt to onnx](https://forums.developer.nvidia.com/t/conversion-from-etlt-to-onnx/302581)

<div class="topic-metadata">

**Author:** [@gupta.nitin.srs](https://forums.developer.nvidia.com/u/gupta.nitin.srs)\
**Replies:** 2\
**Last updated:** [September 3, 2024, 2:01am UTC](https://forums.developer.nvidia.com/t/conversion-from-etlt-to-onnx/302581 "2024-09-03T02:01:05Z")

</div>

provide brief step how to convert model .etlt (resnet18\_vehiclemakenet\_pruned.etlt) to onnx ( resnet18\_vehiclemakenet\_pruned.onnx)

---

## [LLM on Jetson Nano 4GB B01](https://forums.developer.nvidia.com/t/llm-on-jetson-nano-4gb-b01/298618)

<div class="topic-metadata">

**Author:** [@polaris-333](https://forums.developer.nvidia.com/u/polaris-333)\
**Replies:** 12\
**Last updated:** [August 12, 2024, 7:23am UTC](https://forums.developer.nvidia.com/t/llm-on-jetson-nano-4gb-b01/298618 "2024-08-12T07:23:49Z")

</div>

Hi All, I am having Jetson Nano 4GB B01 development board. We want to add LLM on this device locally. I searched on the forum which shares information on NanoLLM, Phi-2 SLM etc. Which will be the best suitable forJetson…

---

## [Installation and usage of gatorTron model without GPU](https://forums.developer.nvidia.com/t/installation-and-usage-of-gatortron-model-without-gpu/295237)

<div class="topic-metadata">

**Author:** [@shehbaz.shaikh](https://forums.developer.nvidia.com/u/shehbaz.shaikh)\
**Replies:** 4\
**Last updated:** [June 7, 2024, 4:33am UTC](https://forums.developer.nvidia.com/t/installation-and-usage-of-gatortron-model-without-gpu/295237 "2024-06-07T04:33:59Z")

</div>

I am trying to use gatorTron LM for AI conversation. After all installations and setups, as per the documentation when i run the command —\>\>\>\> python tools/preprocess\_data.py --input my-corpus.json --outp…

---

## [AttributeError: module 'typing\_extensions' has no attribute 'Self'](https://forums.developer.nvidia.com/t/attributeerror-module-typing-extensions-has-no-attribute-self/272915)

<div class="topic-metadata">

**Author:** [@Pranav.Buradkar](https://forums.developer.nvidia.com/u/Pranav.Buradkar)\
**Replies:** 0\
**Last updated:** [November 15, 2023, 8:25am UTC](https://forums.developer.nvidia.com/t/attributeerror-module-typing-extensions-has-no-attribute-self/272915 "2023-11-15T08:25:58Z")

</div>

Hi, I am using USD Composer 2023.2.0. I am trying to import “Semantic Kernel” in my extension but I am unable to. It throws me following error: AttributeError: module 'typing\_extensions' has no attribute 'Self' In…

---

## [Using Kaldi for speech recognition](https://forums.developer.nvidia.com/t/using-kaldi-for-speech-recognition/170698)

<div class="topic-metadata">

**Author:** [@joepareti54](https://forums.developer.nvidia.com/u/joepareti54)\
**Replies:** 0\
**Last updated:** [March 11, 2021, 2:20pm UTC](https://forums.developer.nvidia.com/t/using-kaldi-for-speech-recognition/170698 "2021-03-11T14:20:23Z")

</div>

I hit a roadblock when trying to use KALDI for a corpus of english language data using a Listen-Attend-Spell code which is designed for Chinese language. I do not know how to transform my VCTK data into kaldi format; th…
