ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-04-07 03:17:10 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

convert : update convert-h5-to-ggml.py (#2840)

Browse Source 
improved handling of missing max_length
This commit is contained in:
Anders Bjarby 2025-03-17 08:41:05 +01:00 committed by GitHub
parent e0f3c9d4dd
commit 4854789751
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
models/convert-h5-to-ggml.py
View File

@ -85,9 +85,15 @@ encoder_added = json.load((dir_model / "added_tokens.json").open( "r", encoding=
hparams = json.load((dir_model / "config.json").open("r", encoding="utf8"))
# Add this block to handle missing 'max_length'
if "max_length" not in hparams:
hparams["max_length"] = hparams.get("max_target_positions", 448)
if "max_length" not in hparams or hparams["max_length"] is None:
hparams["max_length"] = hparams.get("max_target_positions", 448) # Default to 448 if missing
elif not isinstance(hparams["max_length"], int):
try:
hparams["max_length"] = int(hparams["max_length"]) # Convert if necessary
except ValueError:
print(f"Warning: Invalid max_length value '{hparams['max_length']}', using default 448.")
hparams["max_length"] = 448
model = WhisperForConditionalGeneration.from_pretrained(dir_model)
#code.interact(local=locals())