Update README.md and simplify usage

diff --git a/Makefile b/Makefile
index 1203e82229c43ee7770e566dbb35009e0d01b02a..e725dc4d0690ecc8cffb2e6f09b5c3e3655add96 100644 (file)
--- a/Makefile
+++ b/Makefile
@@ -1,5 +1,6 @@
 main: ggml.o main.o
        g++ -o main ggml.o main.o
+       ./main -h
 
 ggml.o: ggml.c ggml.h
        gcc -O3 -mavx -mavx2 -mfma -mf16c -c ggml.c
@@ -11,11 +12,7 @@ main.o: main.cpp ggml.h
 clean:
        rm -f *.o main
 
-# run the program
-run: main
-       ./main
-
-# download the following audio samples into folder "./samples":
+# download a few audio samples into folder "./samples":
 .PHONY: samples
 samples:
        @echo "Downloading samples..."
@@ -28,79 +25,20 @@ samples:
        @ffmpeg -loglevel -0 -y -i samples/gb1.ogg -ar 16000 -ac 1 -c:a pcm_s16le samples/gb1.wav
        @ffmpeg -loglevel -0 -y -i samples/hp0.ogg -ar 16000 -ac 1 -c:a pcm_s16le samples/hp0.wav
 
-.PHONY: tiny.en
-tiny.en: main
-       @echo "Downloading tiny.en (75 MB just once)"
-       @mkdir -p models
-       @if [ ! -f models/ggml-tiny.en.bin ]; then \
-               wget --quiet --show-progress -O models/ggml-tiny.en.bin https://ggml.ggerganov.com/ggml-model-whisper-tiny.en.bin ; \
-       fi
-       @echo ""
-       @echo "==============================================="
-       @echo "Running tiny.en on all samples in ./samples ..."
-       @echo "==============================================="
-       @echo ""
-       @for f in samples/*.wav; do \
-               echo "----------------------------------------------" ; \
-               echo "[+] Running base.en on $$f ... (run 'ffplay $$f' to listen)" ; \
-           echo "----------------------------------------------" ; \
-               echo "" ; \
-               ./main -m models/ggml-tiny.en.bin -f $$f ; \
-               echo "" ; \
-       done
 
-.PHONY: base.en
-base.en: main
-       @echo "Downloading base.en (142 MB just once)"
-       @mkdir -p models
-       @if [ ! -f models/ggml-base.en.bin ]; then \
-               wget --quiet --show-progress -O models/ggml-base.en.bin https://ggml.ggerganov.com/ggml-model-whisper-base.en.bin ; \
-       fi
-       @echo ""
-       @echo "==============================================="
-       @echo "Running base.en on all samples in ./samples ..."
-       @echo "==============================================="
-       @echo ""
-       @for f in samples/*.wav; do \
-               echo "----------------------------------------------" ; \
-               echo "[+] Running base.en on $$f ... (run 'ffplay $$f' to listen)" ; \
-           echo "----------------------------------------------" ; \
-               echo "" ; \
-               ./main -m models/ggml-base.en.bin -f $$f ; \
-               echo "" ; \
-       done
+# if not already downloaded, the following targets download the specified model and
+# runs it on all samples in the folder "./samples":
 
+.PHONY: tiny.en
+.PHONY: base.en
+.PHONY: medium.en
 .PHONY: small.en
-small.en: main
-       @echo "Downloading small.en (466 MB just once)"
-       @mkdir -p models
-       @if [ ! -f models/ggml-small.en.bin ]; then \
-               wget --quiet --show-progress -O models/ggml-small.en.bin https://ggml.ggerganov.com/ggml-model-whisper-small.en.bin ; \
-       fi
-       @echo ""
-       @echo "==============================================="
-       @echo "Running small.en on all samples in ./samples ..."
-       @echo "==============================================="
-       @echo ""
-       @for f in samples/*.wav; do \
-               echo "----------------------------------------------" ; \
-               echo "[+] Running base.en on $$f ... (run 'ffplay $$f' to listen)" ; \
-           echo "----------------------------------------------" ; \
-               echo "" ; \
-               ./main -m models/ggml-small.en.bin -f $$f ; \
-               echo "" ; \
-       done
 
-.PHONY: medium.en
-medium.en: main
-       @echo "Downloading medium.en (1.5 GB just once)"
-       @mkdir -p models
-       @if [ ! -f models/ggml-medium.en.bin ]; then \
-               wget --quiet --show-progress -O models/ggml-medium.en.bin https://ggml.ggerganov.com/ggml-model-whisper-medium.en.bin ; \
-       fi
+tiny.en base.en medium.en small.en: main
+       bash ./download-ggml-model.sh $@
        @echo ""
        @echo "==============================================="
-       @echo "Running medium.en on all samples in ./samples ..."
+       @echo "Running $@ on all samples in ./samples ..."
        @echo "==============================================="
        @echo ""
        @for f in samples/*.wav; do \
@@ -108,6 +46,6 @@ medium.en: main
                echo "[+] Running base.en on $$f ... (run 'ffplay $$f' to listen)" ; \
            echo "----------------------------------------------" ; \
                echo "" ; \
-               ./main -m models/ggml-medium.en.bin -f $$f ; \
+               ./main -m models/ggml-$@.bin -f $$f ; \
                echo "" ; \
        done

diff --git a/README.md b/README.md
index cb6e60381dbfb5965f5e4b43f2af29c46c9997ad..891a94a1dc8ae83598529ff6873d1e31cc467adf 100644 (file)
--- a/README.md
+++ b/README.md
@@ -8,6 +8,20 @@ C/C++ port of [OpenAI's Whisper](https://github.com/openai/whisper) speech-to-te
 
 ## Usage
 
+To build the main program, run `make`. You can then transribe a `.wav` file like this:
+
+```bash
+$ ./main -f input.wav
+```
+
+Before running the program, make sure to download one of the ggml Whisper models. For example:
+
+```bash
+bash ./download-ggml-model.sh base.en
+```
+
+---
+
 For a quick demo, simply run `make base.en`:
 
 ```bash
@@ -97,12 +111,12 @@ ffmpeg -i input.mp3 -ar 16000 -ac 1 -c:a pcm_s16le output.wav
 
 ## Memory usage
 
-| Model | Mem |
-| ---   | --- |
-| tiny.en | ~600 MB |
-| base.en | ~800 MB |
-| small.en | ~1.6 GB |
-| medium.en | ~3.5 GB |
+| Model | Disk | Mem |
+| ---   | --- | --- |
+| tiny.en | 75 MB | ~600 MB |
+| base.en | 142 MB | ~800 MB |
+| small.en | 466 MB | ~1.6 GB |
+| medium.en | 1.5 GB | ~3.5 GB |
 
 ## ggml format
 
@@ -113,4 +127,6 @@ 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.
+
 For more details, see the conversion script [convert-pt-to-ggml.py](convert-pt-to-ggml.py)

diff --git a/download-ggml-model.sh b/download-ggml-model.sh
new file mode 100755 (executable)
index 0000000..3d5fa50
--- /dev/null
+++ b/download-ggml-model.sh
@@ -0,0 +1,59 @@
+#!/bin/bash
+
+# This script downloads Whisper model files that have already been converted to ggml format.
+# This way you don't have to convert them yourself.
+
+ggml_path=$(dirname $(realpath $0))
+
+# Whisper models
+models=( "tiny.en" "base.en" "small.en" "medium.en" )
+
+# list available models
+function list_models {
+    printf "\n"
+    printf "  Available models:"
+    for model in "${models[@]}"; do
+        printf " $model"
+    done
+    printf "\n\n"
+}
+
+if [ "$#" -ne 1 ]; then
+    printf "Usage: $0 <model>\n"
+    list_models
+
+    exit 1
+fi
+
+model=$1
+
+if [[ ! " ${models[@]} " =~ " ${model} " ]]; then
+    printf "Invalid model: $model\n"
+    list_models
+
+    exit 1
+fi
+
+# download ggml model
+
+printf "Downloading ggml model $model ...\n"
+
+mkdir -p models
+
+if [ -f "models/ggml-$model.bin" ]; then
+    printf "Model $model already exists. Skipping download.\n"
+    exit 0
+fi
+
+wget --quiet --show-progress -O models/ggml-$model.bin https://ggml.ggerganov.com/ggml-model-whisper-$model.bin
+
+if [ $? -ne 0 ]; then
+    printf "Failed to download ggml model $model \n"
+    printf "Please try again later or download the original Whisper model files and convert them yourself.\n"
+    exit 1
+fi
+
+printf "Done! Model '$model' saved in 'models/ggml-$model.bin'\n"
+printf "You can now use it like this:\n\n"
+printf "  $ ./main -m models/ggml-$model.bin -f samples/jfk.wav\n"
+printf "\n"

diff --git a/main.cpp b/main.cpp
index acbaa91cd654f6b3f1a182e7f16e6e077bfa9afb..40835ba72eaebf2e8acce30504de3b39cee673c9 100644 (file)
--- a/main.cpp
+++ b/main.cpp
@@ -117,9 +117,9 @@ struct whisper_params {
     bool verbose = false;
     bool print_special_tokens = false;
 
-    std::string model = "models/whisper-tiny.en/ggml-model.bin"; // model path
+    std::string model = "models/ggml-base.en.bin"; // model path
 
-    std::string fname_inp = "default.wav";
+    std::string fname_inp = "samples/jfk.wav";
 };
 
 void whisper_print_usage(int argc, char ** argv, const whisper_params & params);
@@ -156,6 +156,7 @@ bool whisper_params_parse(int argc, char ** argv, whisper_params & params) {
 }
 
 void whisper_print_usage(int argc, char ** argv, const whisper_params & params) {
+    fprintf(stderr, "\n");
     fprintf(stderr, "usage: %s [options]\n", argv[0]);
     fprintf(stderr, "\n");
     fprintf(stderr, "options:\n");
@@ -1898,7 +1899,6 @@ int main(int argc, char ** argv) {
     const int64_t t_main_start_us = ggml_time_us();
 
     whisper_params params;
-    params.model = "models/whisper-tiny.en/ggml-model.bin";
 
     if (whisper_params_parse(argc, argv, params) == false) {
         return 1;
@@ -1927,6 +1927,7 @@ int main(int argc, char ** argv) {
 
         if (!whisper_model_load(params.model, model, vocab)) {
             fprintf(stderr, "%s: failed to load model from '%s'\n", __func__, params.model.c_str());
+            whisper_print_usage(argc, argv, {});
             return 1;
         }
 
@@ -1939,6 +1940,7 @@ int main(int argc, char ** argv) {
         drwav wav;
         if (!drwav_init_file(&wav, params.fname_inp.c_str(), NULL)) {
             fprintf(stderr, "%s: failed to open WAV file '%s' - check your input\n", argv[0], params.fname_inp.c_str());
+            whisper_print_usage(argc, argv, {});
             return 2;
         }