models : change default hosting to Hugging Face

My Linode is running out of monthly bandwidth due to the big interest in
the project

README.md

@@ -428,11 +428,14 @@ The original models are converted to a custom binary format. This allows to pack
 - vocabulary
 - weights
 
-You can download the converted models using the [models/download-ggml-model.sh](models/download-ggml-model.sh) script or from here:
+You can download the converted models using the [models/download-ggml-model.sh](models/download-ggml-model.sh) script
+or manually from here:
 
-https://ggml.ggerganov.com
+- https://huggingface.co/datasets/ggerganov/whisper.cpp
+- https://ggml.ggerganov.com
 
-For more details, see the conversion script [models/convert-pt-to-ggml.py](models/convert-pt-to-ggml.py) or the README in [models](models).
+For more details, see the conversion script [models/convert-pt-to-ggml.py](models/convert-pt-to-ggml.py) or the README
+in [models](models).
 
 ## Bindings
 

models/README.md

@@ -1,10 +1,13 @@
 ## Whisper model files in custom ggml format
 
 The [original Whisper PyTorch models provided by OpenAI](https://github.com/openai/whisper/blob/main/whisper/__init__.py#L17-L27)
-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 from https://ggml.ggerganov.com
+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. Currently, they are hosted on the following locations:
+
+- https://huggingface.co/datasets/ggerganov/whisper.cpp
+- https://ggml.ggerganov.com
 
 Sample usage:
 

models/download-ggml-model.cmd

@@ -18,7 +18,7 @@ if %argc% neq 1 (
 
 set model=%1
 
-for %%b in (%models%) do ( 
+for %%b in (%models%) do (
   if "%%b"=="%model%" (
     CALL :download_model
     goto :eof
@@ -41,7 +41,7 @@ if exist "ggml-%model%.bin" (
 
 PowerShell -NoProfile -ExecutionPolicy Bypass -Command "Invoke-WebRequest -Uri https://ggml.ggerganov.com/ggml-model-whisper-%model%.bin -OutFile ggml-%model%.bin"
 
-if %ERRORLEVEL% neq 0 ( 
+if %ERRORLEVEL% neq 0 (
   echo Failed to download ggml model %model%
   echo Please try again later or download the original Whisper model files and convert them yourself.
   goto :eof

models/download-ggml-model.sh

@@ -3,6 +3,12 @@
 # This script downloads Whisper model files that have already been converted to ggml format.
 # This way you don't have to convert them yourself.
 
+#src="https://ggml.ggerganov.com"
+#pfx="ggml-model-whisper"
+
+src="https://huggingface.co/datasets/ggerganov/whisper.cpp"
+pfx="resolve/main/ggml"
+
 # get the path of this script
 function get_script_path() {
     if [ -x "$(command -v realpath)" ]; then
@@ -46,7 +52,7 @@ fi
 
 # download ggml model
 
-printf "Downloading ggml model $model ...\n"
+printf "Downloading ggml model $model from '$src' ...\n"
 
 cd $models_path
 
@@ -56,9 +62,9 @@ if [ -f "ggml-$model.bin" ]; then
 fi
 
 if [ -x "$(command -v wget)" ]; then
-    wget --quiet --show-progress -O ggml-$model.bin https://ggml.ggerganov.com/ggml-model-whisper-$model.bin
+    wget --quiet --show-progress -O ggml-$model.bin $src/$pfx-$model.bin
 elif [ -x "$(command -v curl)" ]; then
-    curl --output ggml-$model.bin https://ggml.ggerganov.com/ggml-model-whisper-$model.bin
+    curl --output ggml-$model.bin $src/$pfx-$model.bin
 else
     printf "Either wget or curl is required to download models.\n"
     exit 1