뉴스 및 전체 검색
뉴스, 도구, 모델, 가이드, 주제, 워크플로, 프롬프트를 함께 검색합니다.
AI 모델 149
“Transcript AI”
distil-large-v3
Distil-Whisper was proposed in the paper Robust Knowledge Distillation via Large-Scale Pseudo Labelling. This is the third and final installment of the Distil-Whisper English series. It the knowledge distilled version of OpenAI's Whisper large-v3, the latest and most performant Whisper model to date. Compared to previous Distil-Whisper models, the distillation procedure for distil-large-v3 has been adapted to give **superior long-form transcription accuracy** with OpenAI's **sequential long-form algorithm**.
moonshine-tiny
Moonshine Tiny is a 27M-parameter encoder-decoder speech-recognition model from Moonshine AI (formerly Useful Sensors), introduced in Moonshine: Speech Recognition for Live Transcription and Voice Commands. It transcribes English speech and is designed for fast on-device inference. This repository packages the model for LiteRT: a float32 model, an int8 model (dynamic-range-quantized decoder with a float32 encoder), and ahead-of-time compiled variants for a range of MediaTek and Qualcomm SoCs so the model can run on the device NPU. For an on-device Android demo that runs Moonshine (and other ASR models) with hardware acceleration, see the LiteRT speech recognition sample.
canary-1b-flash-gguf
GGUF conversions of nvidia/canary-1b-flash for use with transcribe.cpp. Ported from upstream commit a9a55e0, pinned 2026-05-08. Validated against the NeMo reference at transcribe.cpp commit db53eda on 2026-05-08. Offline multilingual speech-to-text and translation. A multitask AED with a 32-layer FastConformer encoder and a 4-layer Transformer decoder. Supports automatic speech recognition in English, German, Spanish, and French, and bidirectional EN↔{DE, ES, FR} translation. Takes a 16 kHz mono WAV and produces a transcript. Not a streaming model; word/segment timestamps are upstream-experimental and not exposed in the v1 port.
wav2vec2-base-korean
This model is a fine-tuned version of Facebook's wav2vec2-base model, adapted for Korean language recognition using the Zeroth-Korean dataset. The model has been trained to transcribe Korean speech into text, specifically utilizing the unique jamo characters of the Korean language. The model can be directly used for transcribing Korean speech to text without additional fine-tuning. It is particularly useful for applications requiring accurate Korean language recognition such as voice assistants, transcription services, and language learning tools. This model can be integrated into larger systems that require speech recognition capabilities, such as automated customer service, voice-controlled applications, and more.
MOSS-Transcribe-Diarize
MOSS-Transcribe-Diarize 0.9B is an end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness. It supports transcription and diarization across **50+** languages, single-pass inference on audio recordings up to **90 minutes** long, and custom hotword prompting for domain-specific terms. Given an audio or video file, the model generates a compact speaker-aware transcript in one pass, including timestamps and anonymous speaker labels such as `[S01]`, `[S02]`, and beyond.
VoxCPM2
**VoxCPM2** is a tokenizer-free, diffusion autoregressive Text-to-Speech model — **2B parameters**, **30 languages**, **48kHz** audio output, trained on over **2 million hours** of multilingual speech data. - 🌍 **30-Language Multilingual** — No language tag needed; input text in any supported language directly - 🎨 **Voice Design** — Generate a novel voice from a natural-language description alone (gender, age, tone, emotion, pace…); no reference audio required - 🎛️ **Controllable Cloning** — Clone any voice from a short clip, with optional style guidance to steer emotion, pace, and expression while preserving timbre - 🎙️ **Ultimate Cloning** — Provide reference audio + its transcript for audio-continuation cloning; every vocal nuance faithfully reproduced - 🔊 **48kHz Studio-Quality Output** — Accepts 16kHz reference; outputs 48kHz via AudioVAE V2's built-in super-resolution, no external upsampler needed - 🧠 **Context-Aware Synthesis** — Automatically infers appropriate prosody and expressiveness from text content - ⚡ **Real-Time Streaming** — RTF as low as ~0.3 on NVIDIA RTX 4090, and ~0.13 accelerated by Nano-VLLM - 📜 **Fully Open-Source & Commercial-Ready** — Apache-2.0 license, free for commercial use Arabic, Burmese, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Indonesian, Italian, Japanese, Khmer, Korean, Lao, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Tagalog, Thai, Turkish, Vietnamese
Whisper-Medicalv1CNB1
Ad-hoc generation arguments can be passed to `model.generate`, including `num_beams` for beam-search, `return_timestamps` for segment-level timestamps, and `prompt_ids` for prompting. See the docstrings for more details. Unlike previous Distil-Whisper releases, distil-large-v3 is specifically designed to be compatible with OpenAI's sequential long-form transcription algorithm. This algorithm uses a sliding window for buffered inference of long audio files (> 30-seconds), and returns more accurate transcriptions compared to the chunked long-form algorithm. The sequential long-form algorithm should be used in either of the following scenarios: 1. Transcription accuracy is the most important factor, and latency is less of a consideration 2. You are transcribing **batches** of long audio files, in which case the latency of sequential is comparable to chunked, while being up to 0.5% WER more accurate
whisper-medium-uzbek
**Uzbek automatic speech recognition**, fine-tuned from `openai/whisper-medium` on **753 hours of exclusively human-transcribed Uzbek speech**. This is the **medium** (769M parameters) model in the NavAI Whisper family. It is trained only on data with genuine human transcripts — no pseudo-labels, no scraped audio — and no evaluation test set is present in the training data. Macro WER is the mean Word Error Rate across four held-out Uzbek test sets (see Evaluation). Lower is better. All four models live in the **NavAI Whisper Collection**.
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows. It extends the Nemotron Nano family with integrated video+speech comprehension, Graphical User Interface (GUI), Optical Character Recognition (OCR), and speech transcription capabilities, enabling end-to-end processing of rich enterprise content such as meeting recordings, M&E assets, training videos, and complex business documents. NVIDIA Nemotron 3 Nano Omni was developed by NVIDIA as part of the Nemotron model family. This model was improved using Qwen3-VL-30B-A3B-Instruct, Qwen3.5-122B-A10B, Qwen3.5-397B-A17B, Qwen2.5-VL-72B-Instruct, and gpt-oss-120b. For more information, please see the Training Dataset section below. Governing Terms: Use of this model is governed by the NVIDIA Open Model Agreement
nb-whisper-large
Introducing the **_Norwegian NB-Whisper Large model_**, proudly developed by the National Library of Norway. NB-Whisper is a cutting-edge series of models designed for automatic speech recognition (ASR) and speech translation. These models are based on the work of OpenAI's Whisper. Each model in the series has been trained for 250,000 steps, utilizing a diverse dataset of 8 million samples. These samples consist of aligned audio clips, each 30 seconds long, culminating in a staggering 66,000 hours of speech. For an in-depth understanding of our training methodology and dataset composition, keep an eye out for our upcoming article. While the main models are suitable for most transcription task, we demonstrate how easy it is to change the output of the main model. The following models are trained 250 additional steps from the main models above, and might be suitable for more targetted use cases: - **Verbatim version**: This lower-cased variant is more literal and suitable for tasks requiring detailed transcription, such as linguistic analysis. You can try the models directly through the HuggingFace Inference API, accessible on the right side of this page. Be aware that initially, the model needs to load and will run on limited CPU capacity, which might be slow. To enhance your experience, we are temporarily hosting some models on TPUs for a few days, significantly boosting their performance. Explore these under the **Spaces** section on the Main Page.