openai/whisper-large-v3
openai/whisper-large-v3
2
1
Overview Code Discussions Pull Requests Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Sanchit Gandhi 2024-08-12 10:20:10 +00:00 committed by system
parent afda370583
commit 06f233fe06
No known key found for this signature in database
GPG Key ID: 6A528E38E0733467
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -390,6 +390,7 @@ model = AutoModelForSpeechSeq2Seq.from_pretrained(
# Enable static cache and compile the forward pass
model.generation_config.cache_implementation = "static"
model.generation_config.max_new_tokens = 256
model.forward = torch.compile(model.forward, mode="reduce-overhead", fullgraph=True)
processor = AutoProcessor.from_pretrained(model_id)
@ -409,7 +410,7 @@ sample = dataset[0]["audio"]
# 2 warmup steps
for _ in tqdm(range(2), desc="Warm-up step"):
with sdpa_kernel(SDPBackend.MATH):
result = pipe(sample.copy())
result = pipe(sample.copy(), generate_kwargs={"min_new_tokens": 256, "max_new_tokens": 256})
# fast run
with sdpa_kernel(SDPBackend.MATH):