upstream-archive/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-07-23 11:10:57 -05:00
Code Issues Packages Projects Releases Wiki Activity

whisper : make large version explicit + fix data size units (#1493)

Browse Source
This commit is contained in:
Georgi Gerganov
2023-11-15 19:42:25 +02:00
committed by GitHub
parent 1d79e78402
commit bfbaa4dce5
16 changed files with 69 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
models/README.md
View File

@@ -39,19 +39,19 @@ https://huggingface.co/ggerganov/whisper.cpp/tree/main
## Available models
| Model | Disk | Mem | SHA |
| --- | --- | --- | --- |
| tiny | 75 MB | ~390 MB | `bd577a113a864445d4c299885e0cb97d4ba92b5f` |
| tiny.en | 75 MB | ~390 MB | `c78c86eb1a8faa21b369bcd33207cc90d64ae9df` |
| base | 142 MB | ~500 MB | `465707469ff3a37a2b9b8d8f89f2f99de7299dac` |
| base.en | 142 MB | ~500 MB | `137c40403d78fd54d454da0f9bd998f78703390c` |
| small | 466 MB | ~1.0 GB | `55356645c2b361a969dfd0ef2c5a50d530afd8d5` |
| small.en | 466 MB | ~1.0 GB | `db8a495a91d927739e50b3fc1cc4c6b8f6c2d022` |
| medium | 1.5 GB | ~2.6 GB | `fd9727b6e1217c2f614f9b698455c4ffd82463b4` |
| medium.en | 1.5 GB | ~2.6 GB | `8c30f0e44ce9560643ebd10bbe50cd20eafd3723` |
| large-v1 | 2.9 GB | ~4.7 GB | `b1caaf735c4cc1429223d5a74f0f4d0b9b59a299` |
| large-v2 | 2.9 GB | ~4.7 GB | `0f4c8e34f21cf1a914c59d8b3ce882345ad349d6` |
| large | 2.9 GB | ~4.7 GB | `ad82bf6a9043ceed055076d0fd39f5f186ff8062` |
| Model | Disk | SHA |
| --- | --- | --- |
| tiny | 75 MiB | `bd577a113a864445d4c299885e0cb97d4ba92b5f` |
| tiny.en | 75 MiB | `c78c86eb1a8faa21b369bcd33207cc90d64ae9df` |
| base | 142 MiB | `465707469ff3a37a2b9b8d8f89f2f99de7299dac` |
| base.en | 142 MiB | `137c40403d78fd54d454da0f9bd998f78703390c` |
| small | 466 MiB | `55356645c2b361a969dfd0ef2c5a50d530afd8d5` |
| small.en | 466 MiB | `db8a495a91d927739e50b3fc1cc4c6b8f6c2d022` |
| medium | 1.5 GiB | `fd9727b6e1217c2f614f9b698455c4ffd82463b4` |
| medium.en | 1.5 GiB | `8c30f0e44ce9560643ebd10bbe50cd20eafd3723` |
| large-v1 | 2.9 GiB | `b1caaf735c4cc1429223d5a74f0f4d0b9b59a299` |
| large-v2 | 2.9 GiB | `0f4c8e34f21cf1a914c59d8b3ce882345ad349d6` |
| large-v3 | 2.9 GiB | `ad82bf6a9043ceed055076d0fd39f5f186ff8062` |
## Model files for testing purposes

4
models/convert-h5-to-coreml.py
View File

@@ -78,14 +78,14 @@ def convert_hf_whisper(hf_model_name_or_path: str, whisper_state_path: str):
# Ported from models/convert-whisper-to-coreml.py
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--model-name", type=str, help="name of model to convert (e.g. tiny, tiny.en, base, base.en, small, small.en, medium, medium.en, large, large-v1, large-v2)", required=True)
parser.add_argument("--model-name", type=str, help="name of model to convert (e.g. tiny, tiny.en, base, base.en, small, small.en, medium, medium.en, large-v1, large-v2, large-v3)", required=True)
parser.add_argument("--model-path", type=str, help="path to the model (e.g. if published on HuggingFace: Oblivion208/whisper-tiny-cantonese)", required=True)
parser.add_argument("--encoder-only", type=bool, help="only convert encoder", default=False)
parser.add_argument("--quantize", type=bool, help="quantize weights to F16", default=False)
parser.add_argument("--optimize-ane", type=bool, help="optimize for ANE execution (currently broken)", default=False)
args = parser.parse_args()
if args.model_name not in ["tiny", "tiny.en", "base", "base.en", "small", "small.en", "medium", "medium.en", "large", "large-v1", "large-v2"]:
if args.model_name not in ["tiny", "tiny.en", "base", "base.en", "small", "small.en", "medium", "medium.en", "large-v1", "large-v2", "large-v3"]:
raise ValueError("Invalid model name")
pt_target_path = f"models/hf-{args.model_name}.pt"

4
models/convert-whisper-to-coreml.py
View File

@@ -296,13 +296,13 @@ def convert_decoder(hparams, model, quantize=False):
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--model", type=str, help="model to convert (e.g. tiny, tiny.en, base, base.en, small, small.en, medium, medium.en, large, large-v1, large-v2)", required=True)
parser.add_argument("--model", type=str, help="model to convert (e.g. tiny, tiny.en, base, base.en, small, small.en, medium, medium.en, large-v1, large-v2, large-v3)", required=True)
parser.add_argument("--encoder-only", type=bool, help="only convert encoder", default=False)
parser.add_argument("--quantize", type=bool, help="quantize weights to F16", default=False)
parser.add_argument("--optimize-ane", type=bool, help="optimize for ANE execution (currently broken)", default=False)
args = parser.parse_args()
if args.model not in ["tiny", "tiny.en", "base", "base.en", "small", "small.en", "small.en-tdrz", "medium", "medium.en", "large", "large-v1", "large-v2"]:
if args.model not in ["tiny", "tiny.en", "base", "base.en", "small", "small.en", "small.en-tdrz", "medium", "medium.en", "large-v1", "large-v2", "large-v3"]:
raise ValueError("Invalid model name")
whisper = load_model(args.model).cpu()

4
models/convert-whisper-to-openvino.py
View File

@@ -38,10 +38,10 @@ def convert_encoder(hparams, encoder, mname):
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--model", type=str, help="model to convert (e.g. tiny, tiny.en, base, base.en, small, small.en, medium, medium.en, large, large-v1, large-v2)", required=True)
parser.add_argument("--model", type=str, help="model to convert (e.g. tiny, tiny.en, base, base.en, small, small.en, medium, medium.en, large-v1, large-v2, large-v3)", required=True)
args = parser.parse_args()
if args.model not in ["tiny", "tiny.en", "base", "base.en", "small", "small.en", "medium", "medium.en", "large", "large-v1", "large-v2"]:
if args.model not in ["tiny", "tiny.en", "base", "base.en", "small", "small.en", "medium", "medium.en", "large-v1", "large-v2", "large-v3"]:
raise ValueError("Invalid model name")
whisper = load_model(args.model).cpu()

2
models/download-coreml-model.sh
View File

@@ -19,7 +19,7 @@ function get_script_path() {
models_path="$(get_script_path)"
# Whisper models
models=( "tiny.en" "tiny" "base.en" "base" "small.en" "small" "medium.en" "medium" "large-v1" "large-v2" "large" )
models=( "tiny.en" "tiny" "base.en" "base" "small.en" "small" "medium.en" "medium" "large-v1" "large-v2" "large-v3" )
# list available models
function list_models {

2
models/download-ggml-model.cmd
View File

@@ -8,7 +8,7 @@ popd
set argc=0
for %%x in (%*) do set /A argc+=1
set models=tiny.en tiny base.en base small.en small medium.en medium large-v1 large-v2 large
set models=tiny.en tiny base.en base small.en small medium.en medium large-v1 large-v2 large-v3
if %argc% neq 1 (
echo.

4
models/download-ggml-model.sh
View File

@@ -22,7 +22,7 @@ function get_script_path() {
models_path="$(get_script_path)"
# Whisper models
models=(
models=(
"tiny.en"
"tiny"
"tiny-q5_1"
@@ -42,7 +42,7 @@ models=(
"medium.en-q5_0"
"large-v1"
"large-v2"
"large"
"large-v3"
"large-q5_0"
)