ibm-granite/granite-4.0-1b-speech

`ibm-granite/granite-4.0-1b-speech` powered by vLLM - [Original Model Card](https://huggingface.co/ibm-granite/granite-4.0-1b-speech) - [vLLM Documentation](https://docs.vllm.ai/) ## Transcriptions A…

azureFoundry/HuggingFace/ibm-granite-granite-4.0-1b-speech@1

ibm-granite/granite-4.0-1b-speech powered by vLLM

Transcriptions API

Send Request

You can use cURL or any REST Client to send a request to the Azure ML endpoint with your Azure ML token.

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: multipart/form-data" \
    -F "model="ibm-granite/granite-4.0-1b-speech" \
    -F file="@/path/to/file/audio.mp3"

Supported Parameters

The following are the only mandatory parameters to send in the HTTP POST request to v1/audio/transcriptions.

  • model (string): Model ID used to generate the response, in this case since only a single model is deployed within the same endpoint you can either set it to ibm-granite/granite-4.0-1b-speech or leave it blank instead.
  • file (file): The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

The rest of the parameters are optional, and since this model is powered by vLLM with an OpenAI compatible interface on top for the Audio Transcriptions API for automatic speech recognition, then the I/O interfaces for both transcription and streaming are the same as in OpenAI Audio Transcriptions API.

You can find the whole specification of the allowed parameters in the OpenAI Audio Transcriptions API Specification, or alternatively in the endpoint /openapi.json for the current Azure ML Endpoint.

Specifications & capabilities

Input
audio
Output
text
Published model ID
granite-4.0-1b-speech
Capabilities
audioInput

Evaluations

1–20 / 37

Open ASR Leaderboard

8.13%

source id
openASR
leaderboard name
AMI WER (WER)
dimension
speech
metric
AMI WER (WER)
rank
6
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
AMI WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
32
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

8.32%

source id
openASR
leaderboard name
Earnings22 WER (WER)
dimension
speech
metric
Earnings22 WER (WER)
rank
7
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
Earnings22 WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
42
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

5.51%

source id
openASR
leaderboard name
Voxpopuli WER (WER)
dimension
speech
metric
Voxpopuli WER (WER)
rank
7
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
Voxpopuli WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
32
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

2.5%

source id
openASR
leaderboard name
English · LS Other (WER)
dimension
speech
metric
English · LS Other (WER)
rank
14
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
english
suite
OpenASR official public table
datasets
  • AMI-Cleaned
  • Earnings22-Cleaned-AA-chunked
  • Gigaspeech-Cleaned
  • LS Clean
  • LS Other
  • SPGISpeech
  • URGENT24
  • Voxpopuli-AA-Cleaned
  • URGENT24 Clean
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
English · LS Other (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/english.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
64
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech 🤗
Original result ↗

Open ASR Leaderboard

7.38%

source id
openASR
leaderboard name
English · AMI-Cleaned (WER)
dimension
speech
metric
English · AMI-Cleaned (WER)
rank
15
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
english
suite
OpenASR official public table
datasets
  • AMI-Cleaned
  • Earnings22-Cleaned-AA-chunked
  • Gigaspeech-Cleaned
  • LS Clean
  • LS Other
  • SPGISpeech
  • URGENT24
  • Voxpopuli-AA-Cleaned
  • URGENT24 Clean
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
English · AMI-Cleaned (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/english.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
64
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech 🤗
Original result ↗

Open ASR Leaderboard

7.38%

source id
openASR
leaderboard name
AMI-Cleaned WER (WER)
dimension
speech
metric
AMI-Cleaned WER (WER)
rank
15
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
AMI-Cleaned WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
65
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

2.5%

source id
openASR
leaderboard name
LS Other WER (WER)
dimension
speech
metric
LS Other WER (WER)
rank
16
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
LS Other WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
65
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

1.11%

source id
openASR
leaderboard name
English · LS Clean (WER)
dimension
speech
metric
English · LS Clean (WER)
rank
16
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
english
suite
OpenASR official public table
datasets
  • AMI-Cleaned
  • Earnings22-Cleaned-AA-chunked
  • Gigaspeech-Cleaned
  • LS Clean
  • LS Other
  • SPGISpeech
  • URGENT24
  • Voxpopuli-AA-Cleaned
  • URGENT24 Clean
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
English · LS Clean (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/english.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
64
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech 🤗
Original result ↗

Open ASR Leaderboard

1.11%

source id
openASR
leaderboard name
LS Clean WER (WER)
dimension
speech
metric
LS Clean WER (WER)
rank
16
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
LS Clean WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
65
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

8.51%

source id
openASR
leaderboard name
Gigaspeech WER (WER)
dimension
speech
metric
Gigaspeech WER (WER)
rank
19
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
Gigaspeech WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
32
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

5.16%

source id
openASR
leaderboard name
URGENT2024-Clean WER (WER)
dimension
speech
metric
URGENT2024-Clean WER (WER)
rank
19
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
URGENT2024-Clean WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
57
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

596.814

source id
openASR
leaderboard name
AMI-Cleaned RTFx
dimension
runtime
metric
AMI-Cleaned RTFx
rank
22
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
AMI-Cleaned RTFx
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
49
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

5.16%

source id
openASR
leaderboard name
English · URGENT24 Clean (WER)
dimension
speech
metric
English · URGENT24 Clean (WER)
rank
23
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
english
suite
OpenASR official public table
datasets
  • AMI-Cleaned
  • Earnings22-Cleaned-AA-chunked
  • Gigaspeech-Cleaned
  • LS Clean
  • LS Other
  • SPGISpeech
  • URGENT24
  • Voxpopuli-AA-Cleaned
  • URGENT24 Clean
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
English · URGENT24 Clean (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/english.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
64
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech 🤗
Original result ↗

Open ASR Leaderboard

691.504

source id
openASR
leaderboard name
LS Clean RTFx
dimension
runtime
metric
LS Clean RTFx
rank
24
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
LS Clean RTFx
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
49
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

11.99%

source id
openASR
leaderboard name
URGENT2024 WER (WER)
dimension
speech
metric
URGENT2024 WER (WER)
rank
24
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
URGENT2024 WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
57
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

646.586

source id
openASR
leaderboard name
URGENT2024-Clean RTFx
dimension
runtime
metric
URGENT2024-Clean RTFx
rank
26
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
URGENT2024-Clean RTFx
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
44
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

629.272

source id
openASR
leaderboard name
Gigaspeech-Cleaned RTFx
dimension
runtime
metric
Gigaspeech-Cleaned RTFx
rank
27
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
Gigaspeech-Cleaned RTFx
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
49
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

562.609

source id
openASR
leaderboard name
URGENT2024 RTFx
dimension
runtime
metric
URGENT2024 RTFx
rank
27
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
URGENT2024 RTFx
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
44
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Open ASR Leaderboard

11.99%

source id
openASR
leaderboard name
English · URGENT24 (WER)
dimension
speech
metric
English · URGENT24 (WER)
rank
27
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
english
suite
OpenASR official public table
datasets
  • AMI-Cleaned
  • Earnings22-Cleaned-AA-chunked
  • Gigaspeech-Cleaned
  • LS Clean
  • LS Other
  • SPGISpeech
  • URGENT24
  • Voxpopuli-AA-Cleaned
  • URGENT24 Clean
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
English · URGENT24 (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/english.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
64
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech 🤗
Original result ↗

Open ASR Leaderboard

746.775

source id
openASR
leaderboard name
SPGISpeech RTFx
dimension
runtime
metric
SPGISpeech RTFx
rank
28
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
SPGISpeech RTFx
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
49
benchmark_evaluation
true
source model id
ibm-granite/granite-4.0-1b-speech
Original result ↗

Provider specifications & access

1–1 / 1

ibm-granite/granite-4.0-1b-speech ↗

source model id
HuggingFace/ibm-granite-granite-4.0-1b-speech@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • audio
output_modalities
  • text
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    95 / 100

    source id
    stanfordFMTI
    canonical model id
    azureFoundry/HuggingFace/ibm-granite-granite-4.0-1b-speech@1
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    IBM
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    95 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Original sources

    1–6 / 6

    Hugging Face · ibm-granite/granite-4.0-1b-speech ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    GitHub · Catalog ↗

    Hugging Face · Catalog ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–3 / 3

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace