diff --git a/.gitignore b/.gitignore
index 4d11cbf..d50aeab 100644
--- a/.gitignore
+++ b/.gitignore
@@ -19,3 +19,4 @@
 
 bark_weights/
 build/
+models/
diff --git a/README.md b/README.md
index 2ff2448..9398d55 100644
--- a/README.md
+++ b/README.md
@@ -113,10 +113,14 @@ wget https://huggingface.co/suno/bark/raw/main/vocab.txt
 mv ./vocab.txt ./models/
 
 # convert the model to ggml format
-python3 convert.py --dir-model ./models --out-dir ./ggml_weights/ --vocab-path ./models
+python3 convert.py --dir-model ./models --out-dir ./ggml_weights/ --vocab-path ./models --use-f16
+
+# convert the codec to ggml format
+python3 encodec.cpp/convert.py --dir-model ./models/ --out-dir ./ggml_weights/ --use-f16
+mv ggml_weights/ggml-model.bin ggml_weights/encodec_weights.bin
 
 # run the inference
-./build/examples/main/main -m ./ggml_weights/ -p "this is an audio"
+./build/examples/main/main -m ./ggml_weights/ -em ./ggml_weights/encodec_weights.bin -p "this is an audio"
 ```
 
 ### (Optional) Quantize weights
diff --git a/bark.cpp b/bark.cpp
index 04ea0a7..43e021f 100644
--- a/bark.cpp
+++ b/bark.cpp
@@ -737,7 +737,6 @@ static bool bark_model_load(std::ifstream& fin, gpt_model& model, int n_gpu_laye
 #ifdef GGML_USE_METAL
     if (n_gpu_layers > 0) {
         fprintf(stderr, "%s: using Metal backend\n", __func__);
-        ggml_metal_log_set_callback(ggml_log_callback_default, nullptr);
         model.backend = ggml_backend_metal_init();
         if (!model.backend) {
             fprintf(stderr, "%s: ggml_backend_metal_init() failed\n", __func__);