Update generation config (#5)

- update generation config (cc3b291ccc9166a9a6694be052741112693ff910)
- update readme (8a08efe1c36001d8ca140cb2a723a69f2439e836)

README.md

@@ -66,7 +66,7 @@ inputs = processor(
     return_tensors="pt",
 )
 
-audio_values = model.generate(**inputs, do_sample=True, guidance_scale=3, max_new_tokens=256)
+audio_values = model.generate(**inputs, max_new_tokens=256)
 ```
 
 3. Listen to the audio samples either in an ipynb notebook:

generation_config.json

@@ -2,6 +2,9 @@
   "_from_model_config": true,
   "bos_token_id": 2048,
   "decoder_start_token_id": 2048,
+  "do_sample": true,
+  "guidance_scale": 3.0,
+  "max_length": 1500,
   "pad_token_id": 2048,
   "transformers_version": "4.31.0.dev0"
 }