pnnbao-ump
/

VieNeu-Codec

Model card Files Files and versions

pnnbao-ump commited on Mar 31

Commit

9add205

·

verified ·

1 Parent(s): 95bece1

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -29,8 +29,8 @@ Combine the speaker embedding with content tokens from your LLM (VieNeu-TTS v2):
 ```python
 sess_dec = ort.InferenceSession("vieneu_decoder.onnx")
 audio = sess_dec.run(None, {
-    "content_token": ids,
-    "voice_embedding": embedding
 })[0]
 ```

 ```python
 sess_dec = ort.InferenceSession("vieneu_decoder.onnx")
 audio = sess_dec.run(None, {
+    "content_ids": ids,
+    "voice": embedding
 })[0]
 ```