SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Kyutai-STT] correct model type + model id (#39035)

Browse Source 
* correct model type + model id

* udpate doc

* init fix

* style !!!
This commit is contained in:
eustlb
2025-06-25 18:09:00 +02:00
committed by GitHub
parent dad0e87c79
commit 551e48f182
15 changed files with 29 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/source/en/model_doc/stt.md → docs/source/en/model_doc/kyutai_speech_to_text.md
View File

@@ -36,10 +36,10 @@ from transformers import KyutaiSpeechToTextProcessor, KyutaiSpeechToTextForCondi
# 1. load the model and the processor
torch_device = "cuda" if torch.cuda.is_available() else "cpu"
model_id = "kyutai/stt-2.6b-en"
model_id = "kyutai/stt-2.6b-en-trfs"
processor = KyutaiSpeechToTextProcessor.from_pretrained(model_id)
model = KyutaiSpeechToTextForConditionalGeneration.from_pretrained(model_id, device_map=torch_device)
model = KyutaiSpeechToTextForConditionalGeneration.from_pretrained(model_id, device_map=torch_device, torch_dtype="auto")
# 2. load audio samples
ds = load_dataset(
@@ -69,10 +69,10 @@ from transformers import KyutaiSpeechToTextProcessor, KyutaiSpeechToTextForCondi
# 1. load the model and the processor
torch_device = "cuda" if torch.cuda.is_available() else "cpu"
model_id = "kyutai/stt-2.6b-en"
model_id = "kyutai/stt-2.6b-en-trfs"
processor = KyutaiSpeechToTextProcessor.from_pretrained(model_id)
model = KyutaiSpeechToTextForConditionalGeneration.from_pretrained(model_id, device_map=torch_device)
model = KyutaiSpeechToTextForConditionalGeneration.from_pretrained(model_id, device_map=torch_device, torch_dtype="auto")
# 2. load audio samples
ds = load_dataset(