mrutkows/ granite4.1-speech:2b-plus

19 1 week ago

tools 
ollama run mrutkows/granite4.1-speech:2b-plus

Details

1 week ago

fe4f25a01e6b · 2.9GB ·

model
clip
·
480M
·
F16
model
granite
·
1.63B
·
Q8_0
template
{{- /* ------ MESSAGE PARSING ------ */}} {{- /* Declare the system prompt chunks used for different
license
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US
params
{ "num_ctx": 4096, "temperature": 0 }

Readme

Granite 4.1 Speech

Granite-Speech-4.1 is a compact and efficient speech-language model from IBM, purpose-built for multilingual automatic speech recognition (ASR) and bidirectional automatic speech translation (AST). It was created by modality-aligning an intermediate checkpoint of granite-4.0-1b-base to speech, and trained on 174,000 hours of audio from public corpora plus synthetic data.

Running

Pass a path to a .wav file and a task prompt directly on the command line:

ollama run ibm/granite4.1-speech:2b-plus /path/to/audio.wav "transcribe the speech with proper punctuation and capitalization."

To run the default quantization:

ollama run ibm/granite4.1-speech:2b-plus

To run a specific quantization (e.g., Q4_K_M):

ollama run ibm/granite4.1-speech:2b-plus-q4_K_M /path/to/audio.wav "transcribe the speech with proper punctuation and capitalization."

The model accepts mono, 16 kHz .wav audio. To trigger speech processing, include the <|audio|> token in your prompt. If the model receives an unfamiliar or malformed prompt, it falls back to transcription by default.

Preferred Prompts by Task

Task Prompt
ASR (raw) can you transcribe the speech into a written format?
ASR (punctuation) transcribe the speech with proper punctuation and capitalization.
ASR (keyword biasing) transcribe the speech to text. Keywords: <kw1>, <kw2>, ... (e.g. transcribe the speech to text. Keywords: Kubernetes, gRPC, OpenShift.)
AST (raw) translate the speech to <language>.
AST (punctuation) translate the speech to <language> with proper punctuation and capitalization.

Note: Non-English ASR still requires an English prompt.

Supported Languages

English, French, German, Spanish, Portuguese, and Japanese.

Speech translation (AST) is supported to and from English for the languages above, plus English-to-Italian and English-to-Mandarin.

Intended Use

Granite-Speech-4.1 is designed for enterprise applications that process speech inputs — converting speech to text and translating between English and the supported languages.

Capabilities

  • Multilingual ASR — High-accuracy transcription across six languages, powered by a dual-head CTC conformer encoder (graphemic + BPE outputs) with frame importance sampling.
  • Speech Translation (AST) — Bidirectional translation between English and supported languages, including English-to-Italian and English-to-Mandarin.
  • Punctuation & Truecasing — Produces properly punctuated and capitalized output, including German noun capitalization, via a prompt change.
  • Keyword Biasing — Improved recognition of names, acronyms, and technical jargon when supplied with a keyword list.

Learn more