全站搜索

AI 模型 535

• whisper-large-hy-2↗

  arampacha

• whisper-base-fp16-ov↗

  OpenVINO

• faster-distil-whisper-small.en↗

  Systran

  This repository contains the conversion of distil-whisper/distil-small.en to the CTranslate2 model format. Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the `compute_type` option in CTranslate2.

• yi-whisper-large-v3↗

  ivrit-ai

• whisperkit-hinglish-coreml↗

  nitinh

• bulgarian↗

  BuzzASR

  A monolingual automatic speech recognition model for **Bulgarian**, fine-tuned from openai/whisper-large-v3. Part of **BuzzASR**, a suite of 102 language-specialized ASR models (paper: arXiv:2609.09554, Findings of EMNLP 2026). > 🏆 **State-of-the-art (open-source).** On the combined FLEURS + Common Voice test set, this model > achieves the lowest CER of every open system we compare against: Whisper-large-v3, Omnilingual 1B/7B, MMS, Qwen3-ASR, and Cohere Transcribe. FLEURS + **Common Voice Corpus 25.0** (Mozilla, March 2025; https://commonvoice.mozilla.org/en/datasets), capped per the paper. Text-only data from the **Goldfish** corpus (Chang et al., 2026).

• Whisper-Medicalv1CNB1↗

  dearyoungjo

  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

• faster-whisper-tiny.en↗

  guillaumekln

• whisper-small-khmer-v2-onnx↗

  uddompang

• whisper-medium-uzbek↗

  navai-uz

  **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**.