Topic
Speech & voice
Speech recognition, dictation, text-to-speech and voice models, including my English-Hebrew (Hebrish) work.
16 posts
Datasets for fine-tuning speech recognition on your own voice
A guide to my public Hugging Face datasets of read-aloud sentences for fine-tuning speech recognition: tech, Linux, smart home, AI agents, homophones, Hebrew code-switching and voice notes. What each holds and which to use.
Transcribe a WhatsApp chat export, voice messages included
How to read and transcribe a WhatsApp chat export: WhatsApp Export Unpacker parses the ZIP, transcribes voice messages with Whisper, and builds a text file, PDF and WhatsApp-style HTML viewer, with optional anonymisation of participants.
Contextual Sentence Creator: a 3B model that writes ASR training sentences
A Granite 4.2 3B fine-tune that writes natural sentences using a given term, for recording speech recognition training data. 95.7% of sentences pass the acceptance check; GGUF build included.
Fritter: a Parakeet fine-tune for English tech dictation
Fritter is my Parakeet TDT 0.6B v2 fine-tune for English dictation without Hebrew: tech terms, numbers and brand names. Tech WER falls from 7.53% to 4.01% on my voice. Browser demo and GGUF builds.
Hey Yossi: a custom wake word for Home Assistant
Hey Yossi is a custom wake word for Home Assistant, trained on real recordings, in two builds: openWakeWord for the server and Pi, microWakeWord for ESPHome, Voice PE and Android. 95% recall in testing.
S1-ASR-Cleanup: cleaning up dictation with a fine-tuned S1-mini
A fine-tune of S1-mini by Superwhisper that cleans speech-to-text dictation: paragraphs, dates and money as digits, contractions and fillers handled. 0.6B, with GGUF builds for llama.cpp and phones.
Proofed: could a speech model proofread its own transcript?
An idea in development: fine-tune Parakeet on cleanup alone, so dictation comes out without fillers, with digits and paragraphs, in one pass and with no LLM afterwards. Research done, data being recorded.
Update: a 32 MB model for ASR paragraph breaks
MiniLM-L12-ASR-Paragraph-Breaks replaces my Gemma 3 270M paragraph model: break F1 0.85 against 0.78, 32 MB instead of 437 MB, and it cannot change a word of the transcript.
I had a conversation with my own voice clone
I fine-tuned a text-to-speech model on 88 minutes of my voice, then had a ten-minute conversation with it. My lines are real phone recordings; its lines are generated. Listen, and see how it was made.
The Linux mic slider lies: Mic Monitor shows the real gain
On Linux, the microphone volume slider is not your mic's analog gain: mine was 60 dB out. Mic Monitor is a KDE Plasma tray app that shows the real gain in dB, clipping and noise floor, tuned for dictation and speech recognition.
Adding paragraph breaks to speech-to-text output with Gemma 3 270M
A Gemma 3 270M fine-tune that adds paragraph breaks to flat speech-to-text output and changes nothing else. Small enough for on-device use, with an ONNX export. Break F1 0.78 on 26 held-out memos.
Jachnun and Sabich: the first stable Hebrish models, in depth
A deep dive into the first stable Hebrish models, Jachnun v1.0 and Sabich v1.0: the data, the training recipe, the results against stock Parakeet and Whisper, the formats, and the full white paper.
Hebrish: one home for my English-Hebrew speech models
Hebrish is my one-person, not-for-profit home for English-Hebrew speech models: Jachnun, Sabich, Shakshuka and the Whisper fine-tunes, free apps, open data and benchmarks, all at hebrish.app.
Voice typing that understands Hebrish
Speech-to-text mangles the Hebrew words English speakers in Israel use every day. Hebrish fixes that: free on-device apps for Android, Linux and Windows, the Jachnun and Sabich models, results, and how you can help.
Teaching a podcast to say makolet: a classifier for Hebrew hiding in English
I released a small model on Hugging Face that finds romanised Hebrew words inside English text, so TTS voices like Chatterbox can stop reading them as English. Built for My Weird Prompts.
Voxcast: a small voice-to-text app for when "send the email already" is the bottleneck
An open-source Android app that takes your voice and reshapes it into clean prose, polite emails, AI prompts, or Hebrew messages. Two presets are Hebrew-specific — useful for olim and anyone whose Hebrew register is a daily second-guess.