Add granit speech doc #41360
Open
Add granit speech doc #41360
+46
−1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
eustlb
approved these changes
Oct 6, 2025
Comment on lines
+64
to
+65
| dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation") | ||
| wav = torch.tensor(dataset[0]["audio"]["array"]).unsqueeze(0) # add batch dimension |
There was a problem hiding this comment.
starting from datasets 4.0 this should be directly audio.get_all_samples etc see doc
| device = "cuda" if torch.cuda.is_available() else "cpu" | ||
|
|
||
| # Load model and processor | ||
| model_name = "ibm-granite/granite-speech-3.3-8b" |
There was a problem hiding this comment.
nit but let's use rather model_id
| from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq | ||
| from datasets import load_dataset | ||
|
|
||
| device = "cuda" if torch.cuda.is_available() else "cpu" |
There was a problem hiding this comment.
let's rather use rather device_map="auto" in from_pretrained
| processor = AutoProcessor.from_pretrained(model_name) | ||
| tokenizer = processor.tokenizer | ||
| model = AutoModelForSpeechSeq2Seq.from_pretrained( | ||
| model_name, device_map=device, torch_dtype=torch.bfloat16 |
There was a problem hiding this comment.
torch_dtype is deprecated! let's use dtype. Also dtype="auto" here since
"torch_dtype": "bfloat16" in config.json
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Add usage example for the Granite Speech models
@eustlb