Hacker News with Generative AI: Speech Recognition

Play Dialog: A contextual turn-taking TTS model like NotebookLM Playground (play.ai)
PlayNoteAgentsPlaygroundPricingAPICommunityConversation (2 Speakers)Narration (1 Speaker)LanguageSpeaker 1 VoiceSpeaker 2 VoiceConnecting...Random PromptCreate Voice Clone

Speech Recognition, Artificial Intelligence, Text-to-Speech, Machine Learning

49 points by dulldata 8 days ago | 12 comments

Evaluating OpenAI Whisper's Hallucinations on Different Silences (sabrina.dev)
AI hallucinations in healthcare have made recent headlines, as OpenAI’s speech-to-text model (Whisper) has been shown to hallucinate during silences.

Generative AI, AI Hallucinations, Speech Recognition

8 points by sabrina_ramonov 22 days ago | 1 comments

Moonshine, the new state of the art for speech to text (petewarden.com)
Can you imagine using a keyboard where it took a key press two seconds to show up on screen? That’s the typical latency for most voice interfaces, so it’s no wonder they’ve failed to catch on for most people. Today we’re open sourcing Moonshine, a new speech to text model that returns results faster and more efficiently than the current state of the art, OpenAI’s Whisper, while matching or exceeding its accuracy.

Speech Recognition, Artificial Intelligence, Open Source, Technology, Software

172 points by freediver 25 days ago | 36 comments

Ask HN: Real-time speech-to-speech translation (ycombinator.com)
Has anyone had any luck with a free, offline, open-source, real-time speech-to-speech translation app on under-powered devices (i.e., older smart phones)?

Speech Recognition, Translation, Open Source, Mobile Apps

158 points by thangalin 27 days ago | 70 comments

Moonshine, the new state of the art for speech to text (petewarden.com)
Can you imagine using a keyboard where it took a key press two seconds to show up on screen? That’s the typical latency for most voice interfaces, so it’s no wonder they’ve failed to catch on for most people. Today we’re open sourcing Moonshine, a new speech to text model that returns results faster and more efficiently than the current state of the art, OpenAI’s Whisper, while matching or exceeding its accuracy.

Speech Recognition, Artificial Intelligence, Open Source, Technology

10 points by jamescham 31 days ago | 1 comments

Meta Spirit LM: Open multimodal language model that freely mixes text and speech (twitter.com)

Meta, Language Models, Open Source, Multimodal AI, Speech Recognition

13 points by anjneymidha 33 days ago | 4 comments

Show HN: SpeakMyVoice – App for people with vocal or speech difficulties (speakmyvoice.com)
With SpeakMyVoice, you're always part of the conversation.

Accessibility, Speech Recognition, Communication

44 points by 1mbsite 37 days ago | 7 comments

Omni SenseVoice: High-Speed Speech Recognition with Words Timestamps (github.com/lifeiteng)
Built on SenseVoice, Omni SenseVoice is optimized for lightning-fast inference and precise timestamps—giving you a smarter, faster way to handle audio transcription!

Speech Recognition, Audio Transcription, Software, Open Source

169 points by ringer007 39 days ago | 27 comments

Improving Whisper Transcriptions with GPT-4o (github.com/orcaman)
I was watching the latest news episode from Whisky.com (where fine spirits meet ™) the other day on YouTube, and noticed that the transcription was really off.

AI, OpenAI, Speech Recognition, Transcription

6 points by _orcaman_ 47 days ago | 1 comments

Whisper-Large-v3-Turbo (huggingface.co)
Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting.

Generative AI, Machine Learning, Speech Recognition

5 points by mfiguiere 49 days ago | 0 comments

Show HN: Reverb ASR+Diarization, the Best Open Source ASR for Long-Form Audio (ycombinator.com)
Today, we are launching and open sourcing our current generation ASR models named "Reverb."

Open Source, Speech Recognition, Audio Processing

12 points by leetharris 49 days ago | 1 comments

VoiceRAG: A pattern for RAG and voice with the GPT-4o Realtime API for audio (microsoft.com)
The new Azure OpenAI gpt-4o-realtime-preview model opens the door for even more natural application user interfaces with its speech-to-speech capability.

Generative AI, Artificial Intelligence, Microsoft, Speech Recognition, API

11 points by pmc00 50 days ago | 0 comments

Show HN: Speech-to-speech playground for OpenAI's new Realtime API (livekit.io)
Try OpenAI's new Realtime API right from your browser.

OpenAI, Speech Recognition, Real-time APIs, Web Development

10 points by bcherry 50 days ago | 11 comments

Llama 3.1 Omni Model (github.com/ictnlp)
LLaMA-Omni is a speech-language model built upon Llama-3.1-8B-Instruct, It supports low-latency and high-quality speech interactions, simultaneously generating both text and speech responses based on speech instructions.

Generative AI, Speech Recognition

304 points by taikon 64 days ago | 41 comments

Moshi: A speech-text foundation model for real time dialogue (github.com/kyutai-labs)
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework.

Speech Recognition, Machine Learning, Dialogue Systems

365 points by gkucsko 64 days ago | 64 comments

Speech Dictation Mode for Emacs (lepisma.xyz)
There is a wide range of input mechanisms for computers, starting with keyboards (which are relatively mature) and extending to various types of neural interfaces (currently under research). Speech lies somewhere on this spectrum with a lot of promises but still not much to show for. Keeping accessibility aspects aside, I think speech is mature enough to be used for drafting ideas and taking notes. Maybe not so much for structured writing like programming or final versions of most prose.

Emacs, Speech Recognition, Text Editing, Accessibility

127 points by adityaathalye 69 days ago | 32 comments

Hugging Face tackles speech-to-speech (github.com/huggingface)

Speech Recognition, AI, Software

27 points by andito 79 days ago | 5 comments

Recording and Processing Spoken Word (tratt.net)

Speech Recognition, Audio Processing

20 points by ltratt 92 days ago | 2 comments

A powerful tool for converting speech into text (trintai.com)

Speech Recognition, AI

6 points by allamaso 104 days ago | 5 comments

Language model can listen while speaking (huggingface.co)