Minor

README.md

@@ -12,7 +12,7 @@ High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisp
 - Zero memory allocations at runtime
 - Runs on the CPU
 - [C-style API](https://github.com/ggerganov/whisper.cpp/blob/master/whisper.h)
-- Supported platforms: Linux, Mac OS (Intel and Arm), Raspberry Pi, Android
+- Supported platforms: Linux, Mac OS (Intel and Arm), Windows (MinGW), Raspberry Pi, Android
 
 ## Usage
 
@@ -248,6 +248,8 @@ The original models are converted to a custom binary format. This allows to pack
 - vocabulary
 - weights
 
-You can download the converted models using the [download-ggml-model.sh](download-ggml-model.sh) script.
+You can download the converted models using the [download-ggml-model.sh](download-ggml-model.sh) script or from here:
+
+https://ggml.ggerganov.com
 
 For more details, see the conversion script [convert-pt-to-ggml.py](convert-pt-to-ggml.py) or the README in [models](models).

models/README.md

@@ -4,7 +4,7 @@ The [original Whisper PyTorch models provided by OpenAI](https://github.com/open
 have been converted to custom `ggml` format in order to be able to load them in C/C++. The conversion has been performed using the
 [convert-pt-to-ggml.py](convert-pt-to-ggml.py) script. You can either obtain the original models and generate the `ggml` files
 yourself using the conversion script, or you can use the [download-ggml-model.sh](download-ggml-model.sh) script to download the
-already converted models.
+already converted models from https://ggml.ggerganov.com
 
 Sample usage:
 

whisper.cpp

@@ -2387,7 +2387,7 @@ int whisper_full(
         // print the prompt
         //printf("\n\n");
         //for (int i = 0; i < prompt.size(); i++) {
-        //    printf("%s: prompt[%d] = %s\n", __func__, i, vocab.id_to_token[prompt[i]].c_str());
+        //    printf("%s: prompt[%d] = %s\n", __func__, i, ctx->vocab.id_to_token[prompt[i]].c_str());
         //}
         //printf("\n\n");