Ocular AI (YC W24) (@OcularHQ) header
Ocular AI (YC W24) (@OcularHQ) profile picture

Post-Training Data Research Lab Encoding Human Expertise into Machines. backed by @ycombinator, @drivecapital, @alumniventures

San Francisco
Joined March 2024
Photo by Ocular AI (YC W24) (@OcularHQ)Photo by Ocular AI (YC W24) (@OcularHQ)Photo by Ocular AI (YC W24) (@OcularHQ)Photo by Ocular AI (YC W24) (@OcularHQ)Photo by Ocular AI (YC W24) (@OcularHQ)Photo by Ocular AI (YC W24) (@OcularHQ)Photo by Ocular AI (YC W24) (@OcularHQ)Photo by Ocular AI (YC W24) (@OcularHQ)Photo by Ocular AI (YC W24) (@OcularHQ)
Ocular AI (YC W24) evaluated @NVIDIAAI's latest Nemotron 3.5 Transcribe 30B-A4B ahead of today's release, working with their research team! It ranks #1 among open-weight transcription models and #4 overall across 21 SOTA models on our benchmark, with a 2.95% word error rate. A standout: preserving repetitions, short acknowledgments, and fragmented speech, with the second-lowest deletion count. One scoring detail matters: its spelling of “hm” added 57 insertion errors under our benchmark’s normalization rules. Changing that spelling alone would lower WER to 2.50%—second overall! Congratulations to the @nvidia team! #NVIDIA #Nemotron #SpeechAI #OcularAI
1
1
6
182
🚀 New Research: Post-Training Open TTS Models with Human Data. We fine-tuned 8 models, including NVIDIA Audex-2B & Qwen3-TTS 1.7B, using LoRA & full-weight SFT. Just 1hr 22 minutes of studio-grade, TTS Dataset improved 5 models by up to +13.6 points on alphanumeric reading. @NVIDIAAI @nvidia @Alibaba_Qwen @sesame
2
1
4
162
1/ Results on our held-out alphanumeric TTS benchmark: → @nvidia @NVIDIAAI Audex-2B: 23.6% → 37.2% → Llasa 1B: 14.5% → 28.1% → Spark-TTS: 19.6% → 31.7% → Orpheus 3B: 32.0% → 39.3% → @Alibaba_Qwen Qwen3-TTS: 23.6% → 30.5% Full research, training configurations & evaluation results:
2
47
𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗧𝗵𝗲 𝗖𝗼𝗻𝘃𝗲𝗿𝘀𝗲-𝗗𝗶𝗮𝗿𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝗕𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸 🎙️ Getting the words right is only part of understanding a conversation. 𝗞𝗻𝗼𝘄𝗶𝗻𝗴 𝘄𝗵𝗼 𝘀𝗮𝗶𝗱 𝘁𝗵𝗲𝗺 𝗺𝗮𝘁𝘁𝗲𝗿𝘀 𝘁𝗼𝗼. 11 models. Real-world, two-person American English conversations. Interruptions and overlapping speech included. Models hear a single mix. Separate speaker tracks and time-aligned transcripts provide the reference. Vendor-by-vendor results below ↓ Scores are pooled diarization error rate (DER) on this sample: no collar, overlap included. Lower is better. Leaderboard, report, dataset sample & evaluation harness: useocular.com/converse/diari… #VoiceAI #SpeakerDiarization
3
1
4
504
9/10 • @Meta Muse Voice Transcribe 1.0: 𝟯𝟱.𝟴𝟰% DER. Eleventh overall on this four-conversation sample.
1
23
10/10 • @SpaceXSI (xAI) Two Grok systems evaluated: • Grok Voice Transcribe 2.0: 𝟯𝟭.𝟯𝟯% DER • Grok STT 1.0: 𝟯𝟰.𝟮𝟴% DER Ranked 6th and 10th respectively on this sample.
15
🚀 New Product: we're introducing Default Voices for Text-to-Speech (TTS) models. A catalog of professionally performed, studio-recorded voices that can be licensed for commercial TTS default voice cloning. Each voice comes with: 1. A professional voice actor 2. Studio-recorded performance 3. Distinct and consistent voice identity 4. Commercial synthesis and voice-cloning rights Listen to the voices: useocular.com/human-data/tts… If the voices fit what you're building, send me a message and we’ll share the licensing details. #TextoSpeech #VoiceAI #AI #TTS #ASR
1
1
5
116