Instructions to use ibm-granite/granite-speech-4.1-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-granite/granite-speech-4.1-2b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ibm-granite/granite-speech-4.1-2b")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ibm-granite/granite-speech-4.1-2b") model = AutoModelForMultimodalLM.from_pretrained("ibm-granite/granite-speech-4.1-2b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- AMD Developer Cloud
Upload 8 files
Browse files- .eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_ami_test.jsonl +0 -0
- .eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_earnings22_test.jsonl +0 -0
- .eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_gigaspeech_test.jsonl +0 -0
- .eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_librispeech_test.clean.jsonl +0 -0
- .eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_librispeech_test.other.jsonl +0 -0
- .eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_spgispeech_test.jsonl +3 -0
- .eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_tedlium_test.jsonl +0 -0
- .eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_voxpopuli_test.jsonl +0 -0
- .gitattributes +1 -0
.eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_ami_test.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
.eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_earnings22_test.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
.eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_gigaspeech_test.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
.eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_librispeech_test.clean.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
.eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_librispeech_test.other.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
.eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_spgispeech_test.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f90bb97631d1d2774684f12112ed31b581175b3bf7de83351ae5660f816b1a0d
|
| 3 |
+
size 15286729
|
.eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_tedlium_test.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
.eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_voxpopuli_test.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
multilingual_sample.wav filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
multilingual_sample.wav filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
.eval_results/MODEL_ibm-granite-granite-speech-4.1-2b_DATASET_hf-audio-esb-datasets-test-only-sorted_spgispeech_test.jsonl filter=lfs diff=lfs merge=lfs -text
|