models : add usage comments to the HF convert script (#157)

diff --git a/models/convert-h5-to-ggml.py b/models/convert-h5-to-ggml.py
index f236355a4d48a54a155e0497a8a86130b256bf54..b882c4d4ecc4a6edce472bbc8d12890bd7a26ce4 100644 (file)
--- a/models/convert-h5-to-ggml.py
+++ b/models/convert-h5-to-ggml.py
@@ -1,3 +1,20 @@
+# Convert Hugging Face fine-tuned models to ggml format
+#
+# Usage:
+#
+#   git clone https://github.com/openai/whisper
+#   git clone https://github.com/ggerganov/whisper.cpp
+#   git clone https://huggingface.co/openai/whisper-medium
+#
+#   python3 ./whisper.cpp/models/convert-h5-to-ggml.py ./whisper-medium/ ./whisper .
+#
+# This script is similar to "convert-pt-to-ggml.py"
+#
+# For more info:
+#
+#   https://github.com/ggerganov/whisper.cpp/issues/157
+#
+
 import io
 import os
 import sys

diff --git a/models/convert-pt-to-ggml.py b/models/convert-pt-to-ggml.py
index ef4759f663b9adf2e9ee3974ec7efce79094698c..5cf9cf9541d03addd95075e07a4a674991cb3110 100644 (file)
--- a/models/convert-pt-to-ggml.py
+++ b/models/convert-pt-to-ggml.py
@@ -44,107 +44,107 @@ import numpy as np
 #from transformers import GPT2TokenizerFast
 
 # ref: https://github.com/openai/whisper/blob/8cf36f3508c9acd341a45eb2364239a3d81458b9/whisper/tokenizer.py#L10-L110
-LANGUAGES = {
-    "en": "english",
-    "zh": "chinese",
-    "de": "german",
-    "es": "spanish",
-    "ru": "russian",
-    "ko": "korean",
-    "fr": "french",
-    "ja": "japanese",
-    "pt": "portuguese",
-    "tr": "turkish",
-    "pl": "polish",
-    "ca": "catalan",
-    "nl": "dutch",
-    "ar": "arabic",
-    "sv": "swedish",
-    "it": "italian",
-    "id": "indonesian",
-    "hi": "hindi",
-    "fi": "finnish",
-    "vi": "vietnamese",
-    "iw": "hebrew",
-    "uk": "ukrainian",
-    "el": "greek",
-    "ms": "malay",
-    "cs": "czech",
-    "ro": "romanian",
-    "da": "danish",
-    "hu": "hungarian",
-    "ta": "tamil",
-    "no": "norwegian",
-    "th": "thai",
-    "ur": "urdu",
-    "hr": "croatian",
-    "bg": "bulgarian",
-    "lt": "lithuanian",
-    "la": "latin",
-    "mi": "maori",
-    "ml": "malayalam",
-    "cy": "welsh",
-    "sk": "slovak",
-    "te": "telugu",
-    "fa": "persian",
-    "lv": "latvian",
-    "bn": "bengali",
-    "sr": "serbian",
-    "az": "azerbaijani",
-    "sl": "slovenian",
-    "kn": "kannada",
-    "et": "estonian",
-    "mk": "macedonian",
-    "br": "breton",
-    "eu": "basque",
-    "is": "icelandic",
-    "hy": "armenian",
-    "ne": "nepali",
-    "mn": "mongolian",
-    "bs": "bosnian",
-    "kk": "kazakh",
-    "sq": "albanian",
-    "sw": "swahili",
-    "gl": "galician",
-    "mr": "marathi",
-    "pa": "punjabi",
-    "si": "sinhala",
-    "km": "khmer",
-    "sn": "shona",
-    "yo": "yoruba",
-    "so": "somali",
-    "af": "afrikaans",
-    "oc": "occitan",
-    "ka": "georgian",
-    "be": "belarusian",
-    "tg": "tajik",
-    "sd": "sindhi",
-    "gu": "gujarati",
-    "am": "amharic",
-    "yi": "yiddish",
-    "lo": "lao",
-    "uz": "uzbek",
-    "fo": "faroese",
-    "ht": "haitian creole",
-    "ps": "pashto",
-    "tk": "turkmen",
-    "nn": "nynorsk",
-    "mt": "maltese",
-    "sa": "sanskrit",
-    "lb": "luxembourgish",
-    "my": "myanmar",
-    "bo": "tibetan",
-    "tl": "tagalog",
-    "mg": "malagasy",
-    "as": "assamese",
-    "tt": "tatar",
-    "haw": "hawaiian",
-    "ln": "lingala",
-    "ha": "hausa",
-    "ba": "bashkir",
-    "jw": "javanese",
-    "su": "sundanese",
-}
+#LANGUAGES = {
+#    "en": "english",
+#    "zh": "chinese",
+#    "de": "german",
+#    "es": "spanish",
+#    "ru": "russian",
+#    "ko": "korean",
+#    "fr": "french",
+#    "ja": "japanese",
+#    "pt": "portuguese",
+#    "tr": "turkish",
+#    "pl": "polish",
+#    "ca": "catalan",
+#    "nl": "dutch",
+#    "ar": "arabic",
+#    "sv": "swedish",
+#    "it": "italian",
+#    "id": "indonesian",
+#    "hi": "hindi",
+#    "fi": "finnish",
+#    "vi": "vietnamese",
+#    "iw": "hebrew",
+#    "uk": "ukrainian",
+#    "el": "greek",
+#    "ms": "malay",
+#    "cs": "czech",
+#    "ro": "romanian",
+#    "da": "danish",
+#    "hu": "hungarian",
+#    "ta": "tamil",
+#    "no": "norwegian",
+#    "th": "thai",
+#    "ur": "urdu",
+#    "hr": "croatian",
+#    "bg": "bulgarian",
+#    "lt": "lithuanian",
+#    "la": "latin",
+#    "mi": "maori",
+#    "ml": "malayalam",
+#    "cy": "welsh",
+#    "sk": "slovak",
+#    "te": "telugu",
+#    "fa": "persian",
+#    "lv": "latvian",
+#    "bn": "bengali",
+#    "sr": "serbian",
+#    "az": "azerbaijani",
+#    "sl": "slovenian",
+#    "kn": "kannada",
+#    "et": "estonian",
+#    "mk": "macedonian",
+#    "br": "breton",
+#    "eu": "basque",
+#    "is": "icelandic",
+#    "hy": "armenian",
+#    "ne": "nepali",
+#    "mn": "mongolian",
+#    "bs": "bosnian",
+#    "kk": "kazakh",
+#    "sq": "albanian",
+#    "sw": "swahili",
+#    "gl": "galician",
+#    "mr": "marathi",
+#    "pa": "punjabi",
+#    "si": "sinhala",
+#    "km": "khmer",
+#    "sn": "shona",
+#    "yo": "yoruba",
+#    "so": "somali",
+#    "af": "afrikaans",
+#    "oc": "occitan",
+#    "ka": "georgian",
+#    "be": "belarusian",
+#    "tg": "tajik",
+#    "sd": "sindhi",
+#    "gu": "gujarati",
+#    "am": "amharic",
+#    "yi": "yiddish",
+#    "lo": "lao",
+#    "uz": "uzbek",
+#    "fo": "faroese",
+#    "ht": "haitian creole",
+#    "ps": "pashto",
+#    "tk": "turkmen",
+#    "nn": "nynorsk",
+#    "mt": "maltese",
+#    "sa": "sanskrit",
+#    "lb": "luxembourgish",
+#    "my": "myanmar",
+#    "bo": "tibetan",
+#    "tl": "tagalog",
+#    "mg": "malagasy",
+#    "as": "assamese",
+#    "tt": "tatar",
+#    "haw": "hawaiian",
+#    "ln": "lingala",
+#    "ha": "hausa",
+#    "ba": "bashkir",
+#    "jw": "javanese",
+#    "su": "sundanese",
+#}
 
 ## ref: https://github.com/openai/whisper/blob/8cf36f3508c9acd341a45eb2364239a3d81458b9/whisper/tokenizer.py#L273-L292
 #def build_tokenizer(path_to_whisper_repo: str, name: str = "gpt2"):