Deepgram VS Kaldi

Deepgram Reviews

1. suz11    

   10 months ago
   Fast

   It's fast - but for an API, not the fastest speech-to-text. For a long while I hadn't done research and trusted them. Then tried Whisper and Picovoice. On-device latency is nothing comparable with cloud APIs. If latency is important go with Whisper or Picovoice. If customization is also important go with Picovoice.

   don't get me wrong it's still faster than amazon, Microsoft or Assemblyai

   🏁 Competitors: Picovoice.ai, Google Cloud Speech API, AssemblyAI, Speechmatics, Microsoft Azure, Amazon

   👍 Pros:    Fast|Fast sales|A free demo|Supports multiple languages

   👎 Cons:    Slow support for free customers|Limited free version

Kaldi Reviews

Deepgram mentions (27)

• Building a Live Proctoring System to Detect Multiple Speakers

  Lastly, we will be using Deepgram Audio Diarization APIs to get speaker details from a sample audio clip. - Source: dev.to / 4 months ago

• How do I begin building AI tools for myself?

  There are other AI-powered APIs out there to consider, too. For example, Deepgram can be used to transcribe audio (better than Whisper, offered by OpenAI), ElevenLabs can be used to generate speech from text (including using custom voices, which OpenAI's TTS can't currently do), etc. Depending on what you're trying to make, a combination of these services may be what you need. In any case, Python is going to be... Source: 5 months ago

• Use Langchain, Deepgram, and Mistral 7B to Build a Youtube Video Summarization App

  This guide delves deep into the world of YouTube video summarization, harnessing the power of cutting-edge technologies including Deepgram for superior audio transcription, Langchain for harvesting the power of the LLM, and Mistral 7B, a state-of-the-art and open-source LLM. - Source: dev.to / 6 months ago

• Create a realtime closed captioning solution with Deepgram and Ably

  Historically it's been challenging to provide closed captioning for live experiences, be it a live interview, a sports game with commentary, or a livestream. But Deepgram's AI tooling has changed this, allowing users to easily convert realtime streams of audio into accurate transcripts. - Source: dev.to / 6 months ago

• Introducing Daily's AI-powered Clinical Notes API

  To deliver the best possible output, we’ve tested a wide range of AI models and supporting tools. Today, we’re producing industry-leading clinical notes text by combining Deepgram’s highly capable transcription models, ScienceIO’s healthcare-specific AI for processing medical data, and the Microsoft Azure OpenAI GPT-4 large language model. We’ve worked closely with all three teams to bring this new capability to... - Source: dev.to / 7 months ago

Kaldi mentions (12)

• Amazon plans to charge for Alexa in June–unless internal conflict delays revamp

  Yeah, whisper is the closest thing we have, but even it requires more processing power than is present in most of these edge devices in order to feel smooth. I've started a voice interface project on a Raspberry Pi 4, and it takes about 3 seconds to produce a result. That's impressive, but not fast enough for Alexa. From what I gather a Pi 5 can do it in 1.5 seconds, which is closer, so I suspect it's only a... - Source: Hacker News / 3 months ago

• Steve's Explanation of the Viterbi Algorithm

  You can study CTC in isolation, ignoring all the HMM background. That is how CTC was also originally introduced, by mostly ignoring any of the existing HMM literature. So e.g. Look at the original CTC paper. But I think the distill.pub article (https://distill.pub/2017/ctc/) is also good. For studying HMMs, any speech recognition lecture should cover that. We teach that at RWTH Aachen University but I don't think... - Source: Hacker News / 7 months ago

• Best text to speech softwares

  I also tried Kaldi but the build process was too much for my tiny brain; I've also heard good things about vosk but didn't try that. Source: about 1 year ago

• The Advantages and disadvantages of In-House Speech Acknowledgment

  Frameworks as well as toolkits like Kaldi were at first promoted by the research study area, yet nowadays used by both scientists and also market experts, reduced the access obstacle in the advancement of automatic speech recognition systems. Nonetheless, cutting edge methods need big speech data readies to achieve a usable system. Source: over 1 year ago

• Machine Learning with Unix Pipes

  If you interested in unix-like software design and not yet familiar with kaldi toolkit, you definitely need to check it https://kaldi-asr.org It extended Unix design with archives, control lists and matrices and enabled really flexible unix-like processing. For example, recognition of a dataset looks like this: extract-wav scp:list.scp ark:- | compute-mfcc-feats ark:- ark:- | lattice-decoder-faster final.mdl... - Source: Hacker News / over 1 year ago