全站搜索
AI 模型 535
- faster-whisper-medium-int8↗
rhasspy
- whisper-large-v3-slovenian↗
yuriyvnv
- faster-whisper-tiny↗
guillaumekln
- whisper-medium-khmer↗
seanghay
- whisper-large-v3-turbo-turkish↗
selimc
- faster-whisper-large-v3-ca-punctuated-3370h↗
BSC-LT
- whisper-large-v3-bn-cv17↗
bijaykumarsingh
- whisper-podlodka-turbo↗
bond005
Whisper-Podlodka-Turbo is a new fine-tuned version of a Whisper large-v3-turbo. The main goal of the fine-tuning is to improve the quality of speech recognition and speech translation for Russian and English, as well as reduce the occurrence of hallucinations when processing non-speech audio signals. **Whisper-Podlodka-Turbo** is a new fine-tuned version of Whisper-Large-V3-Turbo, optimized for high-quality Russian speech recognition with proper punctuation + capitalization and enhanced with noise resistance capability. **Whisper-Podlodka-Turbo** is supported in Hugging Face 🤗 Transformers. To run the model, first install the Transformers library. For this example, we'll also install 🤗 Datasets to load toy audio dataset from the Hugging Face Hub, and 🤗 Accelerate to reduce the model loading time:
- whisper-large-v3-turbo↗
OpenAI
Whisper 是一款最先进的自动语音识别（ASR）和语音翻译模型，由 OpenAI 的 Alec Radford 等人在论文《Robust Speech Recognition via Large-Scale Weak Supervision》中提出。Whisper 在超过 500 万小时的标注数据上进行训练，在零样本设置下展现出强大的泛化能力，适用于众多数据集和领域。Whisper large-v3-turbo 是经过微调的剪枝版 Whisper large-v3。换言之，它与原模型完全相同，只是解码层的数量从 32 层减少到了 4 层。因此，该模型的速度大幅提升，但性能会略有下降。您可以在 这里 的 GitHub 讨论中找到更多详细信息。**免责声明**：本模型卡片的内容部分由 🤗 Hugging Face 团队撰写，部分则直接复制粘贴自原始模型卡片。
- whisper-large-v3-turbo-GGUF↗
oxide-lab
> For this model, you need to modify the example code in candle. To try whisper in candle faster and easier, it's better to use the tiny model → https://huggingface.co/oxide-lab/whisper-tiny-GGUF For most use cases, we recommend **q4_k** format as it provides the best balance of: - Size reduction (~65% large-v3-turboer) - Quality (minimal degradation) - Speed (faster inference than higher quantizations)