IBM更新三款Granite Speech模型
IBM发布Granite Speech 5.0 2B，并更新Granite Speech 5.0 Turbo CTC和Granite Speech 4.1 2B Plus，三款模型均采用Apache 2.0许可并原生支持Transformers。据IBM称，新款2B支持多语种转录与翻译、语言ID提示及最多2,000个术语的关键词偏置；Turbo CTC新增多语种转录和原生标点，4.1 2B Plus则改进说话人归因、时间戳和长音频表现。IBM还报告Granite Speech 5.0 2B平均英文WER为5.06%，Turbo CTC达到19,870 RTFx，但这些数据来自厂商，后者所涉排名被明确称为非官方结果。
此次发布为多语种转录翻译、边缘端高速处理和多说话人录音提供了三款开放许可模型，并带来厂商所称的准确率、速度、时间戳和说话人归因改进。
We're excited to share three updates to IBM's Granite Speech collection: a new speech-language model, granite-speech-5.0-2b, and revised versions of two models the community already uses, granite-speech-5.0-470m-turboctc and granite-speech-4.1-2b-plus. Together they cover the full range of enterprise speech work: transcription and translation with high accuracy, extremely fast transcription at the edge, and recordings where who spoke, and when, matter as much as what was said.
| Model | Status | What's new | Best for |
|---|---|---|---|
granite-speech-5.0-2b | New | More accurate, noise- and reverb-robust automatic speech recognition (ASR), language-ID prompting, 2,000-term keyword biasing, better long-form translation | High-accuracy multilingual transcription and translation |
granite-speech-5.0-470m-turboctc | Updated | Multilingual, native punctuation and capitalization, and more robust to noise and reverb | High-throughput and on-device transcription |
granite-speech-4.1-2b-plus | Updated | Improved speaker attribution, timestamps, keyword biasing, and long-speech performance | Meetings, calls, and other multi-speaker recordings |
Granite Speech 5.0 2B: more accurate, more robust, more control
granite-speech-5.0-2b is the successor to granite-speech-4.1-2b at the same parameter count. It transcribes English, French, German, Spanish, Portuguese, and Japanese, and translates to and from English in those languages, plus English to Italian and Mandarin. It was trained on 390,000 hours of public audio, plus synthetic data built for Japanese ASR, keyword biasing, and translation.
#IBM#Granite Speech 5.0 2B#Granite Speech 5.0 Turbo CTC#Granite Speech 4.1 2B Plus#Transformers#vLLM#llama.cpp#MLX Audio#Granite Guardian