Sad to see all the non Chinese open source models being at least one generation behind.

Interestingly they explicitly mention AI generated voices, does that mean voices generated by traditional TTS engines are fine?

Just wanted to share something me and my team have been working on for the last 6 months. I quit my software engineering job at Amazon, and my co-founder quit his aerospace engineering job to build echowin, and it feels amazing to finally get to a phase where we can share it with the world.

echowin picks up phone calls on behalf of your business, and answers the caller's questions and performs business tasks. Our goal is to help businesses stay efficient by saving time, money and resources by automating call handling. We are using multiple models like GPT3, Flan-T5 and others behind the scene to make the magic happen. We have focused on building a solid platform that is extensible and customizable to cater the needs of any type of business.

Here are some of the key capabilities of our platform: - Full natural language understanding. - Personalized dynamic responses for caller's queries. - Free form text knowledge-base that the system uses to answer any questions. - Growing library of "skills" to add more functionality. - Live call transcripts and logs.

We are now available in US and Canada, and are planning on expanding to other countries in the future. I would be happy to answer any questions you may have, and would appreciate any feedback or comments as well.

- K Subedi

Comments URL: https://news.ycombinator.com/item?id=34884912

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=33903212

Points: 1

# Comments: 0

My goal was to help volunteers that were in the field in Nepal communicate in English -> Nepali and back. Even though this was somewhat effective, there was still a communication gap because most people in Nepal in remote parts could not even read in Nepali.

I looked around for solutions but couldn't find any Nepali Text To Speech solutions. The builder brain in me fired up and I decided to build a Nepali Text To Speech engine using some of the groundwork that was laid by Madan Puraskar Pustakalaya (Big Library in Nepal) which they had abandoned halfway.

I spend all night hacking along to build a web app that let the volunteers paste translated text and have it spoken. The result was https://nepalispeech.com/ and the first iteration of this was built in just 13 ish hours.

I hope the people that got affected by the earthquake are in a better situation now.

I left this feedback a bunch of times with different people in the org and I really hope they scrap their janky "frameworks" and dev tooling. They should just move to more standard open source tools options that evolve and get better quicker than barely maintained internal tooling.

Open Source tools also have bigger communities and resources online to debug and solve issues, compared to mediocre documentation from internal wiki. If absolutely needed, make thin wrappers above open source tools. Some other teams within Amazon had the luxury of using better tools, but I bet a lot of people are in the shoes I was in.

I had to switch from OpenAI's models to GPT-J because OpenAI's policies were restrictive. How did you get around that? My guess is that since you are only outputting Emoji's it might be allowed.

Comments URL: https://news.ycombinator.com/item?id=33170899

Points: 3

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=32919785

Points: 23

# Comments: 48