Implement custom dataset class for ASR benchmarking (#41576)

Signed-off-by: Yasmin Moslem <48152713+ymoslem@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Yasmin Moslem
2026-05-12 12:17:58 +08:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 630492da30
commit 28ee78af54
3 changed files with 216 additions and 12 deletions
+6 -2
View File
@@ -9,8 +9,9 @@ from vllm.benchmarks.datasets.datasets import (
BlazeditDataset,
BurstGPTDataset,
ConversationDataset,
CustomAudioDataset,
CustomDataset,
CustomMMDataset,
CustomImageDataset,
HuggingFaceDataset,
InstructCoderDataset,
MLPerfDataset,
@@ -36,6 +37,7 @@ from vllm.benchmarks.datasets.datasets import (
is_valid_sequence,
lora_path_on_disk,
lora_tokenizer_cache,
process_audio,
process_image,
process_video,
zeta_prompt,
@@ -51,7 +53,8 @@ __all__ = [
"BurstGPTDataset",
"ConversationDataset",
"CustomDataset",
"CustomMMDataset",
"CustomAudioDataset",
"CustomImageDataset",
"HuggingFaceDataset",
"InstructCoderDataset",
"MLPerfDataset",
@@ -77,6 +80,7 @@ __all__ = [
"is_valid_sequence",
"lora_path_on_disk",
"lora_tokenizer_cache",
"process_audio",
"process_image",
"process_video",
"RangeRatio",