PulseAugur
中
实时 21:05:38
English(EN) Cactus Compute's Whistle, a 16.9 MB speech-to-text model that runs on a CPU, was benchmarked against Whisper base. On LibriSpeech test-other it scored a 10.47%

Cactus Compute 的 Whistle 语音转文本模型在 CPU 上性能优于 Whisper

Cactus Compute 开发了 Whistle,一个紧凑的 16.9 MB 语音转文本模型,旨在高效运行在 CPU 上。在 LibriSpeech test-other 数据集上的基准测试显示,使用贪婪解码时,Whistle 的词错误率为 10.47%,比 Whisper base 模型好 2.19 个百分点。此外,在十秒音频片段上,Whistle 的速度比 Whisper 快 5.7 倍。 AI

影响 为语音转文本任务提供了一个更高效、CPU 绑定的替代方案,可能降低推理成本。

排序理由 该条目描述了一个新模型发布及其与现有模型的基准性能。 [lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Cactus Compute 的 Whistle 语音转文本模型在 CPU 上性能优于 Whisper

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该条目描述了一个新模型发布及其与现有模型的基准性能。 [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
1 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Cactus Compute's Whistle, a 16.9 MB speech-to-text model that runs on a CPU, was benchmarked against Whisper base. On LibriSpeech test-other it scored a 10.47%

    Cactus Compute's Whistle, a 16.9 MB speech-to-text model that runs on a CPU, was benchmarked against Whisper base. On LibriSpeech test-other it scored a 10.47% word error rate, 2.19 points better than greedy Whisper base, while beam search showed no gap. It ran 5.7 times faster o…