From: Anders Bjarby <redacted>
Date: Mon, 17 Mar 2025 07:41:05 +0000 (+0100)
Subject: convert : update convert-h5-to-ggml.py (#2840)
X-Git-Tag: upstream/1.7.5~140
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=4854789751aa3eed3bbe605a789cc34701b44f10;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

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

improved handling of missing max_length
---

diff --git a/models/convert-h5-to-ggml.py b/models/convert-h5-to-ggml.py
index 5474d586..4d50af46 100644
--- a/models/convert-h5-to-ggml.py
+++ b/models/convert-h5-to-ggml.py
@@ -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())