Cách sử dụng NVIDIA Nemotron 3.5 Transcribe miễn phí

说明与用途

Nemotron 3.5 Transcribe 是 NVIDIA 发布的免费高精度 ASR 模型，可在本地 GPU 上运行或通过免费 Space 演示使用。支持 40 种语言、最长 1 小时音频、最多 8 位说话人分离、词级时间戳和翻译。

问题

Need a free, high‑accuracy speech‑to‑text solution that can be run locally or via free demos.

结果

Users can transcribe up to one hour of audio per request, support 40 languages, speaker diarization up to eight speakers, word‑level timestamps, and translation to 31 languages, all for free when self‑hosted or via the demo.

工作流

• 1. Choose a free route: NVIDIA Space demo, community Spaces, or self‑hosted weights.
• 2. For Space demo: open https://huggingface.co/spaces/nvidia/nemotron-transcribe, select a tab (Karaoke, Podcast, Subtitles), upload or link a sample, run and view output.
• 3. For self‑hosted: install transformers via pip, load model with AutoModelForMultimodalLM and AutoProcessor, prepare audio file, call processor.apply_transcription_request, generate, and decode output.
• 4. For batch or production: deploy with vLLM 0.32.0 and NeMo Speech plugin to expose an OpenAI‑compatible endpoint.
• 5. Monitor GPU usage and choose appropriate precision (BF16, FP8, NVFP4) based on hardware (H100, A100, RTX 5090).

证据

Nemotron 3.5 Transcribe (full name NVIDIA‑Nemotron‑3.5‑Transcribe‑30B‑A4B) was released on 28 Oct 2026 under OpenMDW‑1.1, allowing commercial use.

来源

It achieves a mean WER of 5.33% on the Open ASR leaderboard, ranking 9th out of 61 models.

来源

The Space demo is free, no login required, but only previews 60 seconds and shares GPU resources.

来源