4 LLM frameworks to build AI apps with voice data
Вставка
- Опубліковано 9 чер 2024
- In this video we'll look at 4 LLM frameworks to build AI apps with voice data:
- LeMUR: www.assemblyai.com/docs/getti...
- LangChain: www.langchain.com/langchain
- LlamaIndex: www.llamaindex.ai/
- Haystack: haystack.deepset.ai/
Get your Free Token for AssemblyAI👇
www.assemblyai.com/?...
More Resources:
- Playground: www.assemblyai.com/playground
- LangChain Q&A with RAG: python.langchain.com/docs/use...
- RAG Tutorial: • How to use LangChain f...
▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬
🖥️ Website: www.assemblyai.com
🐦 Twitter: / assemblyai
🦾 Discord: / discord
▶️ Subscribe: ua-cam.com/users/AssemblyAI?...
🔥 We're hiring! Check our open roles: www.assemblyai.com/careers
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#MachineLearning #DeepLearning #AI - Наука та технологія
What if I dont want assembly AI?
Then you could also use those frameworks but probably have to implement your own custom audio data loader
Speech Recognition with a Twist: Instead of a standard speech-to-text project, focus on recognizing different voices or accents. This can be helpful for speaker identification or creating more personalized voice assistant experiences.
If i have multiple persons voice.I have trained data set.How to predict proper speaker identify.
If i ask through my video my voice assistant. Who am i ?My voice assistant tell me you are sanjay.But if a another ask to assistant.who am i? My voice assistant can't say.
Mean focas this project proper speaker identify.
If i say my phone. My voice is my password.It open because i have already trained data set .But if another person say my phone my voice is my password.My voice can't detection who is say it.
Please make a video .How to detect proper speaker identification ?