use float16 instead of bfloat16 as we are inferencing on cpu

README.md

@@ -1,11 +1,11 @@
 ---
 license: apache-2.0
 language:
-- en
+  - en
 tags:
-- text-to-speech
+  - text-to-speech
 base_model:
-- sesame/csm-1b
+  - sesame/csm-1b
 pipeline_tag: text-to-speech
 ---
 
@@ -75,7 +75,7 @@ model_args = ModelArgs(
     audio_vocab_size=2051,
     audio_num_codebooks=32,
 )
-model = Model(model_args).to(device=device, dtype=torch.bfloat16)
+model = Model(model_args).to(device=device, dtype=torch.float16)
 loaded = load_file(model_path)
 model.load_state_dict(loaded)
 
@@ -155,4 +155,4 @@ By using this model, you agree to comply with all applicable laws and ethical gu
 ---
 
 ## Authors
-Johan Schalkwyk, Ankit Kumar, Dan Lyth, Sefik Emre Eskimez, Zack Hodari, Cinjon Resnick, Ramon Sanabria, Raven Jiang, and the Sesame team.
+Johan Schalkwyk, Ankit Kumar, Dan Lyth, Sefik Emre Eskimez, Zack Hodari, Cinjon Resnick, Ramon Sanabria, Raven Jiang, and the Sesame team.