新闻与全站搜索
关联新闻、工具、模型、指南、专题、工作流与提示词。
AI 模型 97
“Transcripti”
whisper-large-gguf
GGUF conversions of openai/whisper-large for use with transcribe.cpp. Ported from upstream commit 4ef9b41, pinned 2026-04-25. Validated against the transformers reference at transcribe.cpp commit 0a26478 on 2026-09-13. OpenAI Whisper large — converted to GGUF for transcribe.cpp. Multilingual transcription, language detection, and speech translation (audio in any supported language → English text). Encoder-decoder transformer; 30-second windows with chunked long-form decoding.
Confucius4-R2T2
Confucius4-R2T2: A Low Latency and High Accuracy Real-Time Speech Recognition Model Confucius4-R2T2 is a low-latency and high-accuracy true streaming Automatic Speech Recognition (ASR) model that features fine-grained and configurable decoding chunks from 80 ms to 2 s. The model operates in append-only output mode: committing transcript text permanently without revising previous words, which is critical for applications where text must be processed or acted upon instantly. This results in a smoother user experience, avoiding disruptive text revisions and visual flickering in real-time applications, such as Real-Time Live Captioning & Subtitling, Downstream NLP Pipelines & LLM Agents, Simultaneous Speech Translation, etc. R2T2, short for Real Real-Time Transcription, is built upon the Qwen3-ASR model. And it is trained with a unique set of data construction techniques including stable-prefix data, forced time-alignment data, and token-level audio segmentation. Combined with a Longest Stable Prefix (LSP) learning paradigm (tech report will be released soon), R2T2 can dynamically determine when a stable prefix can be safely emitted and when additional audio context is needed. By exposing only stable prefixes, the model provides high-quality context that conditions subsequent predictions while guaranteeing that previously emitted text remains unchanged. Despite its streaming design, R2T2 maintains strong accuracy in offline recognition.
Audar-ASR-V1-Turbo
🧭 Overview · 📊 Benchmarks · 💻 GGUF Deploy · 🤗 Transformers · 🎙️ Streaming · ⚡ vLLM · 📄 Tech Report · 🐙 GitHub · ☁️ Audar API · 📜 License **Audar-ASR-V1-Turbo** is an **Arabic-first generative speech-recognition model** — the accuracy tier of the Audar-ASR family. It recasts transcription as **audio-conditioned next-token prediction** over a unified text vocabulary (a language-model decoder rather than a CTC or transducer objective), and is built on a permissively-licensed open-weight audio-LLM foundation and adapted in-house — the contribution is the adaptation (the data curriculum and the alignment rubric), not the foundation: The result is **state-of-the-art dialectal Arabic ASR** — the lowest average WER *and* CER of any evaluated system on the *Open Universal Arabic ASR Leaderboard*. It transcribes MSA and every major Arabic dialect, code-switched Arabic–English, and English, across **30 languages** in total.
LightOnOCR-3-4B
**Best OCR model.** LightOnOCR-3-4B is the largest and most accurate model of the LightOnOCR-3 family, **LightOn's** new generation of lightweight end-to-end OCR models with layout and visual understanding. We recommend it for most OCR tasks. LightOnOCR-3 is a new family of highly performant lightweight OCR models. Compared to the previous generation, they bring significant improvements in speed and transcription quality and introduce new visual understanding features: the models now output bounding box coordinates with labels for all visual elements of a document, short descriptions of images, and the numerical data of figures and charts. With these capabilities, they offer a ready-to-use, easier-to-maintain alternative to complex document understanding pipelines. The models come in three sizes. The 1B keeps the LightOnOCR-2-1B architecture, while the 0.8B and 4B adopt the Qwen3.5 vision-language architecture, which simplifies integration with existing tools and brings a significant speed-up. All models are released under the Apache 2.0 license for research and commercial use.
qwen3-forced-aligner-0.6b-GGUF
GGUF conversions of `Qwen/Qwen3-ForcedAligner-0.6B` — a single-pass forced aligner that takes any (audio, transcript) pair and predicts per-word/per-token timestamps. Reuses the Qwen3-ASR audio encoder + 28-layer LLM body but swaps the lm_head from `(vocab, d)` to `(5000, d)`: each ` ` placeholder you embed in the input gets a 5000-class softmax over `class * 80 ms` timestamps. Plug it into CrispASR via `-am qwen3-forced-aligner-*.gguf` to get word-level timing on **any** transcription backend — voxtral, voxtral4b, qwen3-asr, granite, parakeet, canary, cohere, even whisper. It's an alternative to the existing `canary-ctc-aligner` second-pass with broader language coverage and 80-ms resolution. The CrispASR C++ runtime auto-detects which variant a loaded GGUF is by reading the lm_head shape from `output.weight.ne[1]` — no separate backend, no separate library.
typhoon-asr-qwen-0.6b-ctx
Thai ASR with **prompt-based contextual biasing**: a LoRA fine-tune (merged, 0.80B params) of `Qwen/Qwen3-ASR-0.6B-hf` that accepts a list of names/terms in the system prompt, boosts the ones that are actually spoken, writes them with the **listed spelling**, and ignores the rest (distractor false alarm rate ≤.0004; non-speech probe 5/5). The economical tier: 2.6× smaller than the 1.7b for ~.09 recall. Plain transcription (CER%, same protocol: gigaspeech2 bench in-domain / TVSpeech out-of-domain 30-s talk-show): † single-digit repetition-loop utterances dominate (0.6b: one utt; Thonburian: three, excluding them 8.39).
LightOnOCR-3-0.8B-GGUF
> LightOnOCR-3-0.8B, developed by lightonai, is the lightest and most efficient model in the LightOnOCR-3 family, designed for end-to-end Optical Character Recognition (OCR) and comprehensive document understanding. Built on the Qwen3.5 vision-language architecture, it streamlines complex document pipelines into a single model featuring two primary modes: a default transcription mode that outputs full-page Markdown text, and a "grounding" mode that returns bounding box coordinates and semantic labels for every visual element. Beyond standard text extraction, the model provides advanced visual understanding by automatically describing images and converting charts into structured HTML data tables. Capable of processing diverse formats—including tables, receipts, forms, multi-column layouts, and math notation—LightOnOCR-3-0.8B offers a fast, versatile, and Apache 2.0-licensed solution for both commercial and research document processing tasks.
granite-speech-4.1-2b-nar
**Model Summary:** Granite-Speech-4.1-2B-NAR is a non-autoregressive (NAR) speech recognition model that formulates ASR as conditional transcript editing. Instead of decoding tokens one at a time, it edits a CTC hypothesis in a single forward pass using a bidirectional LLM, achieving competitive accuracy with faster inference than autoregressive alternatives. The model is based on the **NLE** (Non-autoregressive LLM-based Editing) architecture described in this paper. For applications where accuracy is the primary concern, consider **granite-speech-4.1-2b**, an autoregressive model from the Granite Speech 4.1 family which achieves higher transcription accuracy at the cost of increased inference latency. Granite-speech-4.1-2b produces punctuated and capitalized transcripts, supports AST and keyword-biased recognition, and includes Japanese. When speaker or word-timing information is needed, consider using **granite-speech-4.1-2b-plus**, which extends the above model with speaker-attributed ASR (speaker labels + word transcripts) and word-level timing information.
Whisper-Hindi2Hinglish-Apex
1. **Hinglish as a language**: Native ability to transcribe hindi into hinglish, making it easier to understand and process. 2. **Faster Inference**: The model achieves SOTA performance while being upto 8x faster. 3. **Performance Increase**: ~42% average performance increase versus pretrained model across benchmarking datasets. 4. Ranked #1 on Speech-To-Text Arena, beating competitors on transcription preference metric. ***Note***: - *To accurately measure Hinglish transcription performance, the original Hindi ground truth for each dataset was first transliterated to Hinglish. The WER scores below were calculated against this transliterated reference text.* - *To check our model's real-world performance against other SOTA models please head to our Speech-To-Text Arena arena space.* Flash-Attention 2 can be used to make the transcription fast. If your GPU supports Flash-Attention you can use it by, first installing Flash Attention:
parakeet-tdt-0.6b-v3
`parakeet-tdt-0.6b-v3` is a 600-million-parameter multilingual automatic speech recognition (ASR) model designed for high-throughput speech-to-text transcription. It extends the parakeet-tdt-0.6b-v2 model by expanding language support from English to 25 European languages. The model automatically detects the language of the audio and transcribes it without requiring additional prompting. It is part of a series of models that leverage the Granary [1, 2] multilingual corpus as their primary training dataset. **Supported Languages:** Bulgarian (**bg**), Croatian (**hr**), Czech (**cs**), Danish (**da**), Dutch (**nl**), English (**en**), Estonian (**et**), Finnish (**fi**), French (**fr**), German (**de**), Greek (**el**), Hungarian (**hu**), Italian (**it**), Latvian (**lv**), Lithuanian (**lt**), Maltese (**mt**), Polish (**pl**), Portuguese (**pt**), Romanian (**ro**), Slovak (**sk**), Slovenian (**sl**), Spanish (**es**), Swedish (**sv**), Russian (**ru**), Ukrainian (**uk**) `parakeet-tdt-0.6b-v3`'s key features are built on the foundation of its predecessor, parakeet-tdt-0.6b-v2, and include: