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 149
“Transcript AI”
whisper-medium-gguf
GGUF conversions of openai/whisper-medium for use with transcribe.cpp. Ported from upstream commit abdf7c3, pinned 2026-04-25. Validated against the transformers reference at transcribe.cpp commit 0a26478 on 2026-09-13. OpenAI Whisper medium — 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.
wav2vec2-xls-r-parlaspeech-hr
This model for Croatian ASR is based on the facebook/wav2vec2-xls-r-300m model and was fine-tuned with 300 hours of recordings and transcripts from the ASR Croatian parliament dataset ParlaSpeech-HR v1.0. Notice: ParlaSpeech corpora are currently in the process of enrichment with new features. Follow our progress here: http://clarinsi.github.io/parlaspeech Nikola Ljubešić, Danijel Koržinek, Peter Rupnik, Ivo-Pavao Jazbec. ParlaSpeech-HR -- a freely available ASR dataset for Croatian bootstrapped from the ParlaMint corpus. http://www.lrec-conf.org/proceedings/lrec2022/workshops/ParlaCLARINIII/pdf/2022.parlaclariniii-1.16.pdf
typhoon-whisper-large-v3-ctc
Word- and character-level **timestamps for Thai**: a 29M character-CTC head on the **frozen** `typhoon-ai/typhoon-whisper-large-v3` encoder (pinned revision `748e8a4`, recorded in `config.json`). One encoder pass gives transcription *and* alignment. It is **both an aligner and a compact ASR model**: it force-aligns given text (a transcript or ASR hypothesis) to word/character timestamps, and its greedy CTC decode transcribes directly (`--transcribe`, no text needed). `standalone_align.py` (bundled) has no other dependencies; the frozen encoder downloads automatically at the pinned revision. Files: `head.safetensors`, `config.json` (architecture + encoder id/revision), `ctc_vocab.json` (80-symbol Thai char vocab v1.0.0).
financial-roberta-large-sentiment
Financial-RoBERTa Financial-RoBERTa is a pre-trained NLP model to analyze sentiment of financial text including: Financial Statements, Earnings Announcements, Earnings Call Transcripts, Corporate Social Responsibility (CSR) Reports, Environmental, Social, and Governance (ESG) News, Financial News, Etc. Financial-RoBERTa is built by further training and fine-tuning the RoBERTa Large language model using a large corpus created from 10k, 10Q, 8K, Earnings Call Transcripts, CSR Reports, ESG News, and Financial News text. The model will give softmax outputs for three labels: Positive , Negative or Neutral . How to perform sentiment analysis: The easiest way to use the model for single predictions is Hugging Face's sentiment analysis pipeline, which only needs a couple lines of code as shown in the following example:
parakeet-tdt-0.6b-v2-gguf
GGUF conversions of nvidia/parakeet-tdt-0.6b-v2 for use with transcribe.cpp. Ported from upstream commit 1b149a3, pinned 2026-04-15. Validated against the NeMo reference at transcribe.cpp commit bf0d0b7 on 2026-04-18. Offline English speech-to-text. A Conformer encoder with a TDT/RNNT transducer decoder. Takes a 16 kHz mono WAV and produces a transcript with optional token-level timestamps. Not a streaming model; no multilingual capability (see v3 for that).
Index-Echo-S2TT-GGUF
GGUF packages for native speech-to-text translation with audio.cpp. Chinese speech produces timestamped source transcripts and English, Spanish, or Japanese translations. This port supports **S2TT only**; it does not generate translated speech. **There is room to improve 9B output parity and quantized quality**. Focused PRs with reproducible C++/Python comparisons are welcome. Note that 2B and 9B use the same C++ translation path, including the prompt, audio encoder, decoder implementation, and greedy sampler. 2B orig is parity safe, while 9B orig has drifts. 2B has 24 layers and tied token/output embeddings; 9B has 32 layers and a separate LM head. That can change how sensitive their outputs are to numerical differences, but I have not proved that it explains the 9B mismatch. These files were converted from the official 2B checkpoint at `72fd8bdc9bf8251f1c35f6d6289a950eda154395` and 9B checkpoint at `05f86cb7a38684916e193282b6cc02462ace4043`. Each GGUF embeds the audio tower, connector, text decoder, tokenizer, configuration, and audio.cpp model spec. The unused vision weights are not included.
hayai-ocr-v2.5-nova
**Hayai OCR** is an ultra-lightweight (~150M parameter) vision-to-text model engineered for ultra-fast, crop-level transcription across **Japanese, Chinese, Korean, and English**. Hayai couples **Google's SigLIP2 NaFlex** vision encoder with a **custom 12-layer causal transformer decoder**. It transcribes dense, stylized, horizontal, and vertical text in a single forward pass without requiring an intermediate text-line detection stage (e.g., DBNet/YOLO). > **Note:** Hayai is designed specifically for **crop-level recognition**. For full-page scanning, pair it with a text detector.
parakeet-ultra-gguf
GGUF conversions of moondream/parakeet-ultra for use with transcribe.cpp. Ported from upstream commit 73175eb, pinned 2026-10-04. Validated against the kestrel 0.9.1 (Photon) reference at transcribe.cpp commit 08f9e6f0 on 2026-10-05. Moondream's post-trained parakeet-tdt-0.6b-v3. Offline multilingual speech-to-text over the same 25 European languages, with lower error rates than v3 on English and on every FLEURS language we measured. A FastConformer encoder with a TDT transducer decoder, plus a small voice-activity head that the model uses to cut long recordings at pauses into segments of at most 30 seconds. Takes 16 kHz mono WAV and produces a punctuated, cased transcript with optional token-level timestamps. A drop-in replacement for v3: same size, languages and API. Not a streaming model and does not translate.
multitalker-parakeet-streaming-0.6b-v1-gguf
GGUF conversions of nvidia/multitalker-parakeet-streaming-0.6b-v1 for use with transcribe.cpp. Ported from upstream commit 8749fc7, pinned 2026-07-12. Validated against the NeMo reference at transcribe.cpp commit 3083021 on 2026-08-03. Offline and cache-aware streaming English speech-to-text with punctuation and capitalization. A cache-aware streaming FastConformer encoder with an RNN-T transducer decoder, fine-tuned from nvidia/nemotron-speech-streaming-en-0.6b. Plain GGUFs run the single_speaker_mode ASR path, while bundle GGUFs embed nvidia/diar_streaming_sortformer_4spk-v2.1 and, with `--diarize`, transcribe up to four overlapping speakers into a speaker-tagged transcript. The encoder preserves the upstream att_context_size=[70, 13] (1.12s) cache-aware attention mask; all four latency lookahead settings are selectable.
wav2vec2-french-phonemizer
Fine-tuned facebook/wav2vec2-base-fr-voxpopuli-v2 for **French speech-to-phoneme** (without language model) using the train and validation splits of Common Voice v13. As this model is specifically trained for a speech-to-phoneme task, the output is sequence of IPA-encoded words, without punctuation. If you don't read the phonetic alphabet fluently, you can use this excellent IPA reader website to convert the transcript back to audio synthetic speech in order to check the quality of the phonetic transcription. The model has been finetuned on Commonvoice-v13 (FR) for 14 epochs on a 4x2080 Ti GPUs at Cnam/LMSSC using a ddp strategy and gradient-accumulation procedure (256 audios per update, corresponding roughly to 25 minutes of speech per update -> 2k updates per epoch)