# 🕉️ Garchen Rinpoche Speech SIG Proposal

**URL:** <https://forum.webuddhist.com/t/garchen-rinpoche-speech-sig-proposal/340>\
**Category:** Garchen Rinpoche Speech SIG\
**Created:** [July 8, 2025, 5:39am UTC](https://forum.webuddhist.com/t/garchen-rinpoche-speech-sig-proposal/340 "2025-07-08T05:39:00Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Lhakpa\_Wangyal](https://yyz1.discourse-cdn.com/flex003/user_avatar/forum.webuddhist.com/lhakpa_wangyal/32/381_2.png) [@Lhakpa\_Wangyal](https://forum.webuddhist.com/u/Lhakpa_Wangyal)\
**Post date:** [July 8, 2025, 5:39am UTC](https://forum.webuddhist.com/t/garchen-rinpoche-speech-sig-proposal/340/1 "2025-07-08T05:39:00Z")

</div>

AI-powered transcription of Garchen Rinpoche’s speech.

| SUMMARY | |
| --- | --- |
| **Version:** | 1.1 |
| **Purpose** | Train a custom Speech-to-Text model and its training dataset to accurately transcribe Garchen Rinpoche’s oral teachings, making them accessible and searchable. |
| **Champion(s)** | @DavidYesheNyima@Gade |
| **Communication** | - [Discord Channel](https://discord.gg/Hw2fK6znXY) - [Github Team](https://github.com/orgs/OpenPecha/teams/garchen-rinpoche-speech-sig) - [Google Calendar](https://calendar.google.com/calendar/embed?src=c_b3e5558fd7231d7c4169af5a552904c321f70f0cddca60eb4cd3cbee736fa0e7%2540group.calendar.google.com&ctz=Asia%252FTaipei) |
| **Documentation** | - [PRD (Requirements)](https://forum.webuddhist.com/t/prd-garchen-rinpoche-speech/387) - [Github Project Board](https://github.com/orgs/OpenPecha/projects/121/views/1) - [Visuals](https://link.excalidraw.com/l/9MjBj0OINTj/3D2jflevQMJ) - [Meeting Minutes](https://forum.webuddhist.com/tags/c/sig/garchen/41/minutes) |

* * *

## Proposal Details

### 1. Problem Statement / Motivation

Train a custom Speech-to-Text (STT) model which could automatically turn Rinpoche’s spoken teachings into subtitle-style transcripts (WebVTT). This will help preserve, search, and translate his teachings and making them accessible and searchable in multiple languages.

Creating accurate transcripts isn’t easy due to following reasons;

**Rinpoche’s unique voice:** His age, speech style, and Tibetan dialect make it hard for machines to understand and even for the professional and experienced transcribers.

**Tibetan language issues:** There aren’t many training materials available for Tibetan, especially for religious content.

**Audio problems:** Some recordings are noisy or unclear.

**Special vocabulary:** Buddhist terms used by rinpoche are complex and unfamiliar to regular speech software.

### 2. Previous work

1. **Audio Analysis:** organised and analysed Rinpoche’s audio files to understand their scope, quality, and content.
2. **Model Selection:** After testing three options, a general Tibetan model was chosen as our base because it surprisingly outperformed specialised religious speech models.
3. **Data Collection:** Created a custom training dataset by transcribing over five hours of Rinpoche’s teachings to capture his unique speech.
4. **Custom Training:** Fine-tuned the selected model with this custom data, which significantly reduced its error rate and improved transcription accuracy.
5. **Proven Efficiency:** A final test showed that using the fine-tuned model saved human transcribers 38% of their time, while the basic model sometimes made the process slower.

### 3.Scope

- **In Scope:**
  - **Ideal Goal** : 5% error rate in the text.
  - **Realistic Goal** : Around **15% error rate** , which is still very useful
  - **Main Focus** : Make sure the transcript is **good enough** for translation and searching
  - Detecting **only Rinpoche’s speech**
  - Training and improving the speech model
  - Creating **subtitle files** with time stamps
  - Reducing background noise and fillers
  - Custom STT model for GR

- **Out of Scope:**
  - Translating the teachings
  - Transcribing other speakers

### 3. Potential Deliverables

- A custom model that makes **less than 15% mistakes** on Rinpoche’s clean speech
- Subtitle-style transcripts that are **easy to read and need very little correction**
- A **semi-automated system** that helps with future transcriptions
- A **public tool** where users can upload audio and get automatic subtitles

### 4. Team

**Members:**

- @DavidYesheNyima - Champion
- @Lhakpa_Wangyal - coordinator
- @Ganga_Gyatso - developer

**Annotators:**

- Kunchok Gawa @kunchok73kunchok73kunchok73kunchok73kunchok73kunchok73kunchok73kunchok73

- @KarmatsepKarmatsepKarmatsepKarmatsep

- Ja@jamluv227jamluv227pa Lobsang @jamluv227

- Kalsang Thardoe @K-Thardoe

## SIG Meeting Calendar

- **Meetings:** 2nd Tuesday of each month, 16:00 UTC
- [Meeting Minutes](https://forum.webuddhist.com/tags/c/sig/garchen/41/minutes)

https://calendar.google.com/calendar/embed?src=c_b3e5558fd7231d7c4169af5a552904c321f70f0cddca60eb4cd3cbee736fa0e7%40group.calendar.google.com&ctz=Asia%2FKolkata
## Related SIGs and Groups

- [OpenPecha QA](https://openpecha.org/qa)
- [OpenPecha Packaging Committee](https://openpecha.org/packaging)

## Useful Links

- [Garchen Teachings to Read](https://garchen.net/library-teachings-transcripts-to-read/)