holm/whisper.cpp
1
1
Fork 0
forked from extern/whisper.cpp
Code Issues Pull Requests Packages Projects Releases Wiki Activity

extra : compute SHA of all models files

Browse Source
This commit is contained in:
Georgi Gerganov 2022-11-02 18:31:55 +02:00
parent 02dfd5b8c3
commit b5dde365e9
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
3 changed files with 45 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
README.md
View File

@ -59,8 +59,8 @@ For a quick demo, simply run `make base.en`:
```java ```java
$ make base.en $ make base.en
cc -I. -O3 -std=c11 -pthread -DGGML_USE_ACCELERATE -c ggml.c cc -I. -O3 -std=c11 -pthread -DGGML_USE_ACCELERATE -c ggml.c -o ggml.o
c++ -I. -I./examples -O3 -std=c++11 -pthread -c whisper.cpp c++ -I. -I./examples -O3 -std=c++11 -pthread -c whisper.cpp -o whisper.o
c++ -I. -I./examples -O3 -std=c++11 -pthread examples/main/main.cpp whisper.o ggml.o -o main -framework Accelerate c++ -I. -I./examples -O3 -std=c++11 -pthread examples/main/main.cpp whisper.o ggml.o -o main -framework Accelerate
./main -h ./main -h
@ -70,13 +70,17 @@ options:
-h, --help show this help message and exit -h, --help show this help message and exit
-s SEED, --seed SEED RNG seed (default: -1) -s SEED, --seed SEED RNG seed (default: -1)
-t N, --threads N number of threads to use during computation (default: 4) -t N, --threads N number of threads to use during computation (default: 4)
-p N, --processors N number of processors to use during computation (default: 1)
-ot N, --offset-t N time offset in milliseconds (default: 0) -ot N, --offset-t N time offset in milliseconds (default: 0)
-on N, --offset-n N segment index offset (default: 0) -on N, --offset-n N segment index offset (default: 0)
-mc N, --max-context N maximum number of text context tokens to store (default: max)
-wt N, --word-thold N word timestamp probability threshold (default: 0.010000)
-v, --verbose verbose output -v, --verbose verbose output
--translate translate from source language to english --translate translate from source language to english
-otxt, --output-txt output result in a text file -otxt, --output-txt output result in a text file
-ovtt, --output-vtt output result in a vtt file -ovtt, --output-vtt output result in a vtt file
-osrt, --output-srt output result in a srt file -osrt, --output-srt output result in a srt file
-owts, --output-words output word-level timestamps to a text file
-ps, --print_special print special tokens -ps, --print_special print special tokens
-pc, --print_colors print colors -pc, --print_colors print colors
-nt, --no_timestamps do not print timestamps -nt, --no_timestamps do not print timestamps
@ -114,23 +118,26 @@ whisper_model_load: n_text_layer = 6
whisper_model_load: n_mels = 80 whisper_model_load: n_mels = 80
whisper_model_load: f16 = 1 whisper_model_load: f16 = 1
whisper_model_load: type = 2 whisper_model_load: type = 2
whisper_model_load: mem_required = 505.00 MB whisper_model_load: mem_required = 670.00 MB
whisper_model_load: adding 1607 extra tokens whisper_model_load: adding 1607 extra tokens
whisper_model_load: ggml ctx size = 163.43 MB whisper_model_load: ggml ctx size = 140.60 MB
whisper_model_load: memory size = 22.83 MB whisper_model_load: memory size = 22.83 MB
whisper_model_load: model size = 140.54 MB whisper_model_load: model size = 140.54 MB
main: processing 'samples/jfk.wav' (176000 samples, 11.0 sec), 4 threads, lang = en, task = transcribe, timestamps = 1 ... system_info: n_threads = 4 / 10 | AVX2 = 0 | AVX512 = 0 | NEON = 1 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 |
[00:00.000 --> 00:11.000] And so my fellow Americans, ask not what your country can do for you, ask what you can do for your country. main: processing 'samples/jfk.wav' (176000 samples, 11.0 sec), 4 threads, 1 processors, lang = en, task = transcribe, timestamps = 1 ...
whisper_print_timings: load time = 87.21 ms [00:00:00.000 --> 00:00:11.000] And so my fellow Americans, ask not what your country can do for you, ask what you can do for your country.
whisper_print_timings: mel time = 24.26 ms
whisper_print_timings: sample time = 3.87 ms
whisper_print_timings: encode time = 323.67 ms / 53.94 ms per layer whisper_print_timings: load time = 105.91 ms
whisper_print_timings: decode time = 83.25 ms / 13.87 ms per layer whisper_print_timings: mel time = 24.62 ms
whisper_print_timings: total time = 522.66 ms whisper_print_timings: sample time = 3.63 ms
whisper_print_timings: encode time = 324.71 ms / 54.12 ms per layer
whisper_print_timings: decode time = 83.58 ms / 13.93 ms per layer
whisper_print_timings: total time = 542.81 ms
``` ```
The command downloads the `base.en` model converted to custom `ggml` format and runs the inference on all `.wav` samples in the folder `samples`. The command downloads the `base.en` model converted to custom `ggml` format and runs the inference on all `.wav` samples in the folder `samples`.
@ -172,8 +179,8 @@ make large
| Model | Disk | Mem | SHA | | Model | Disk | Mem | SHA |
| --- | --- | --- | --- | | --- | --- | --- | --- |
| tiny | 75 MB | ~280 MB | `bd577a113a864445d4c299885e0cb97d4ba92b5f` | | tiny | 75 MB | ~390 MB | `bd577a113a864445d4c299885e0cb97d4ba92b5f` |
| base | 142 MB | ~430 MB | `465707469ff3a37a2b9b8d8f89f2f99de7299dac` | | base | 142 MB | ~500 MB | `465707469ff3a37a2b9b8d8f89f2f99de7299dac` |
| small | 466 MB | ~1.0 GB | `55356645c2b361a969dfd0ef2c5a50d530afd8d5` | | small | 466 MB | ~1.0 GB | `55356645c2b361a969dfd0ef2c5a50d530afd8d5` |
| medium | 1.5 GB | ~2.6 GB | `fd9727b6e1217c2f614f9b698455c4ffd82463b4` | | medium | 1.5 GB | ~2.6 GB | `fd9727b6e1217c2f614f9b698455c4ffd82463b4` |
| large | 2.9 GB | ~4.7 GB | `b1caaf735c4cc1429223d5a74f0f4d0b9b59a299` | | large | 2.9 GB | ~4.7 GB | `b1caaf735c4cc1429223d5a74f0f4d0b9b59a299` |
@ -315,7 +322,7 @@ https://user-images.githubusercontent.com/1991296/199337538-b7b0c7a3-2753-4a88-a
## Implementation details ## Implementation details
- The core tensor operations are implemented in C ([ggml.h](ggml.h) / [ggml.c](ggml.c)) - The core tensor operations are implemented in C ([ggml.h](ggml.h) / [ggml.c](ggml.c))
- The high-level C-style API is implemented in C++ ([whisper.h](whisper.h) / [whisper.cpp](whisper.cpp)) - The transformer model and the high-level C-style API are implemented in C++ ([whisper.h](whisper.h) / [whisper.cpp](whisper.cpp))
- Sample usage is demonstrated in [main.cpp](examples/main) - Sample usage is demonstrated in [main.cpp](examples/main)
- Sample real-time audio transcription from the microphone is demonstrated in [stream.cpp](examples/stream) - Sample real-time audio transcription from the microphone is demonstrated in [stream.cpp](examples/stream)
- Various other examples are available in the [examples](examples) folder - Various other examples are available in the [examples](examples) folder

7
extra/sha-all.sh Executable file
View File

@ -0,0 +1,7 @@
#!/bin/bash
# Compute the SHA1 of all model files in ./models/ggml-*.bin
for f in ./models/ggml-*.bin; do
shasum "$f" -a 1
done

14
models/README.md
View File

@ -22,6 +22,20 @@ A third option to obtain the model files is to download them from Hugging Face:
https://huggingface.co/datasets/ggerganov/whisper.cpp/tree/main https://huggingface.co/datasets/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 | 2.9 GB | ~4.7 GB | `b1caaf735c4cc1429223d5a74f0f4d0b9b59a299` |
## Model files for testing purposes ## Model files for testing purposes
The model files pefixed with `for-tests-` are empty (i.e. do not contain any weights) and are used by the CI for testing purposes. The model files pefixed with `for-tests-` are empty (i.e. do not contain any weights) and are used by the CI for testing purposes.