Card: Listen section (spoken project introduction, hebrish.app/updates, 2026-10-22)
Browse files
README.md
CHANGED
|
@@ -63,6 +63,39 @@ Words English already says acceptably are deliberately **not** flagged: *Shabbat
|
|
| 63 |
|
| 64 |
**The whole TTS pipeline** (detect, transliterate, niqqud, tag, speak), with code, real outputs and a white paper: [Hebrish-ASR/English-Hebrew-Code-Switching-TTS-Pipeline](https://github.com/Hebrish-ASR/English-Hebrew-Code-Switching-TTS-Pipeline) 路 [PDF](https://hebrish.app/whitepaper/code-switching-tts-pipeline.pdf).
|
| 65 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
## The author's note (audio)
|
| 67 |
|
| 68 |
Six and a half minutes on why this model exists, recorded the day after release.
|
|
|
|
| 63 |
|
| 64 |
**The whole TTS pipeline** (detect, transliterate, niqqud, tag, speak), with code, real outputs and a white paper: [Hebrish-ASR/English-Hebrew-Code-Switching-TTS-Pipeline](https://github.com/Hebrish-ASR/English-Hebrew-Code-Switching-TTS-Pipeline) 路 [PDF](https://hebrish.app/whitepaper/code-switching-tts-pipeline.pdf).
|
| 65 |
|
| 66 |
+
<!-- hebrish-listen:begin -->
|
| 67 |
+
## Listen: what Hebrish is and how it's made
|
| 68 |
+
|
| 69 |
+
A spoken introduction to the project by the person who makes it: why Hebrish exists, why stock
|
| 70 |
+
speech-to-text gets Hebrew words wrong, how the fine-tunes are trained, the model lines (Sabich,
|
| 71 |
+
Jachnun, Shakshuka, Meorav), how the training data is recorded, and the plans for the apps.
|
| 72 |
+
|
| 73 |
+
| | |
|
| 74 |
+
| --- | --- |
|
| 75 |
+
| Listen | [hebrish.app/updates](https://hebrish.app/updates): player, chapters, edited transcript, MP3 download |
|
| 76 |
+
| Author | Daniel Rosehill |
|
| 77 |
+
| Recorded | 2026-10-22 |
|
| 78 |
+
| Runtime | 1:07:03 |
|
| 79 |
+
|
| 80 |
+
Chapters (each opens the player at that point):
|
| 81 |
+
[0:00](https://hebrish.app/updates#t=0) Why this voice note 路
|
| 82 |
+
[1:36](https://hebrish.app/updates#t=96) Coming to speech to text 路
|
| 83 |
+
[6:36](https://hebrish.app/updates#t=396) Why Hebrew words go wrong 路
|
| 84 |
+
[9:23](https://hebrish.app/updates#t=563) How the fine-tune works 路
|
| 85 |
+
[12:27](https://hebrish.app/updates#t=747) Why Parakeet, and the model plan 路
|
| 86 |
+
[17:44](https://hebrish.app/updates#t=1064) Disfluencies, shekels, paragraphs 路
|
| 87 |
+
[25:40](https://hebrish.app/updates#t=1540) Tech vocabulary and Meorav 路
|
| 88 |
+
[29:07](https://hebrish.app/updates#t=1747) The kitchen sink: Sabich and Jachnun 路
|
| 89 |
+
[33:35](https://hebrish.app/updates#t=2015) Licensing, accents, noisy recordings 路
|
| 90 |
+
[39:10](https://hebrish.app/updates#t=2350) One recorder for ASR and TTS 路
|
| 91 |
+
[41:04](https://hebrish.app/updates#t=2464) Desktop shortcuts and the macro pad 路
|
| 92 |
+
[43:34](https://hebrish.app/updates#t=2614) Android: Bluetooth and one button 路
|
| 93 |
+
[45:35](https://hebrish.app/updates#t=2735) Streaming and Shakshuka 路
|
| 94 |
+
[50:28](https://hebrish.app/updates#t=3028) Long-form transcription 路
|
| 95 |
+
[56:00](https://hebrish.app/updates#t=3360) Output modes 路
|
| 96 |
+
[63:01](https://hebrish.app/updates#t=3781) Report a word, and more voices
|
| 97 |
+
<!-- hebrish-listen:end -->
|
| 98 |
+
|
| 99 |
## The author's note (audio)
|
| 100 |
|
| 101 |
Six and a half minutes on why this model exists, recorded the day after release.
|