# NVIDIA-NeMo/Speech

> NVIDIA framework for training, fine-tuning and deploying speech models: ASR, TTS, speaker diarization and Speech LLMs on PyTorch. Ships pre-trained checkpoints and recipes for researchers and developers.

- Magnitude: 2.0 out of 10 — Steady
- Stars: 18,655 total · +2 stars measured 2026-10-30, 10:49–13:08 UTC, ≈ 6 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2019-08-05 · Last push: 2026-10-30
- GitHub: https://github.com/NVIDIA-NeMo/Speech · Homepage: https://docs.nvidia.com/nemo/speech/nightly/index.html · Page: https://gitnova.dev/en/r/NVIDIA-NeMo/Speech

## Useful for

- Run speech recognition with a pre-trained Parakeet or Canary checkpoint
- Fine-tune a MagpieTTS model on a custom dataset for a new language
- Deploy streaming ASR with controllable latency via the NGC container

## Why it’s here

- Star-counter measurements on 2026-10-30 (UTC), 10:49–13:08: 18653 → 18655 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +5 stars, using observed gains and the previous day.
- Elevated gains were measured on the last 2 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #8, +14 stars.
- Recent forks include notable developers: @nouraellm (665 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3,668
- Issues and pull requests: 15,647
- Watchers: 230
- Average over the last week: 7 per day
- Usual pace: 4 per day
- Stars in the last hour (measured): 0
- Latest release: v3.0.0 (2026-08-07)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-01 … 2026-10-30: 6, 1, 4, 5, 6, 5, 5, 5, 2, 5, 1, 3, 5, 6, 8, 4, 6, 5, 3, 5, 4, 2, 4, 2, 6, 4, 3, 14, 13, 2

## Spotted in now

- GitHub Trending Python today: #8, +14 stars

## Similar by description

1. **ml-explore/mlx** — 1.4 · Steady · Language models · C++ · +1 star measured 2026-10-30, 00:23–13:12 UTC, ≈ 3 by evening
   MLX is an array and machine learning framework from Apple, optimized for Apple silicon with unified memory and lazy computation. Its Python, C++, C, and Swift APIs mirror NumPy and PyTorch, simplifying model training and deployment.
   Full card: https://gitnova.dev/en/r/ml-explore/mlx.md
2. **Tencent-Hunyuan/Hy-SimulMT** — 1.1 · Cooling · Language models · Python · +2 stars measured 2026-10-30, 00:19–13:14 UTC, ≈ 4 by evening
   Tencent Hunyuan's simultaneous speech translation model for real-time bidirectional Chinese-English translation with voice cloning. The repository provides the SimulInfer inference service and SimulTrain training tools.
   Full card: https://gitnova.dev/en/r/Tencent-Hunyuan/Hy-SimulMT.md
3. **OpenWhispr/openwhispr** — 2.9 · Steady · Productivity & self-hosted · JavaScript · +25 stars measured 2026-10-30, 00:17–13:04 UTC, ≈ 51 by evening
   Cross-platform desktop voice-to-text dictation app that transcribes speech locally (Whisper, NVIDIA Parakeet) or in the cloud and pastes text into any app. It also transcribes meetings, manages notes, and connects to AI assistants.
   Full card: https://gitnova.dev/en/r/OpenWhispr/openwhispr.md
4. **tensorflow/tensorflow** — 2.4 · Steady · Language models · C++ · +8 stars measured 2026-10-30, 00:20–13:06 UTC, ≈ 17 by evening
   An open source machine learning platform from Google Brain with Python and C++ APIs for training and deploying neural networks. Used by researchers and developers of ML applications.
   Full card: https://gitnova.dev/en/r/tensorflow/tensorflow.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-30 13:16 UTC, updated every 30 minutes.