Skip to content

Commit

Permalink
Merge pull request #320 from Wordcab/319-add-modified-faster-whisper-…
Browse files Browse the repository at this point in the history
…library

319 add modified faster whisper library
  • Loading branch information
info-wordcab authored Jun 29, 2024
2 parents 61be1ab + 3664171 commit 09ba169
Show file tree
Hide file tree
Showing 41 changed files with 6,521 additions and 1 deletion.
31 changes: 31 additions & 0 deletions faster-whisper/CONTRIBUTING.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
# Contributing to faster-whisper

Contributions are welcome! Here are some pointers to help you install the library for development and validate your changes before submitting a pull request.

## Install the library for development

We recommend installing the module in editable mode with the `dev` extra requirements:

```bash
git clone https://github.com/SYSTRAN/faster-whisper.git
cd faster-whisper/
pip install -e .[dev]
```

## Validate the changes before creating a pull request

1. Make sure the existing tests are still passing (and consider adding new tests as well!):

```bash
pytest tests/
```

2. Reformat and validate the code with the following tools:

```bash
black .
isort .
flake8 .
```

These steps are also run automatically in the CI when you open the pull request.
21 changes: 21 additions & 0 deletions faster-whisper/LICENSE
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
MIT License

Copyright (c) 2023 SYSTRAN

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
4 changes: 4 additions & 0 deletions faster-whisper/MANIFEST.in
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
include faster_whisper/assets/silero_vad.onnx
include requirements.txt
include requirements.conversion.txt
include faster_whisper/assets/pyannote_vad_model.bin
320 changes: 320 additions & 0 deletions faster-whisper/README.md

Large diffs are not rendered by default.

Binary file added faster-whisper/benchmark/benchmark.m4a
Binary file not shown.
94 changes: 94 additions & 0 deletions faster-whisper/benchmark/memory_benchmark.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
import argparse
import time

from typing import Callable

import py3nvml.py3nvml as nvml

from memory_profiler import memory_usage
from utils import MyThread, get_logger, inference

logger = get_logger("faster-whisper")
parser = argparse.ArgumentParser(description="Memory benchmark")
parser.add_argument(
"--gpu_memory", action="store_true", help="Measure GPU memory usage"
)
parser.add_argument("--device-index", type=int, default=0, help="GPU device index")
parser.add_argument(
"--interval",
type=float,
default=0.5,
help="Interval at which measurements are collected",
)
args = parser.parse_args()
device_idx = args.device_index
interval = args.interval


def measure_memory(func: Callable[[], None]):
if args.gpu_memory:
logger.info(
"Measuring maximum GPU memory usage on GPU device."
" Make sure to not have additional processes running on the same GPU."
)
# init nvml
nvml.nvmlInit()
handle = nvml.nvmlDeviceGetHandleByIndex(device_idx)
gpu_name = nvml.nvmlDeviceGetName(handle)
gpu_memory_limit = nvml.nvmlDeviceGetMemoryInfo(handle).total >> 20
gpu_power_limit = nvml.nvmlDeviceGetPowerManagementLimit(handle) / 1000.0
info = {"gpu_memory_usage": [], "gpu_power_usage": []}

def _get_gpu_info():
while True:
info["gpu_memory_usage"].append(
nvml.nvmlDeviceGetMemoryInfo(handle).used >> 20
)
info["gpu_power_usage"].append(
nvml.nvmlDeviceGetPowerUsage(handle) / 1000
)
time.sleep(interval)

if stop:
break

return info

stop = False
thread = MyThread(_get_gpu_info, params=())
thread.start()
func()
stop = True
thread.join()
result = thread.get_result()

# shutdown nvml
nvml.nvmlShutdown()
max_memory_usage = max(result["gpu_memory_usage"])
max_power_usage = max(result["gpu_power_usage"])
print("GPU name: %s" % gpu_name)
print("GPU device index: %s" % device_idx)
print(
"Maximum GPU memory usage: %dMiB / %dMiB (%.2f%%)"
% (
max_memory_usage,
gpu_memory_limit,
(max_memory_usage / gpu_memory_limit) * 100,
)
)
print(
"Maximum GPU power usage: %dW / %dW (%.2f%%)"
% (
max_power_usage,
gpu_power_limit,
(max_power_usage / gpu_power_limit) * 100,
)
)
else:
logger.info("Measuring maximum increase of memory usage.")
max_usage = memory_usage(func, max_usage=True, interval=interval)
print("Maximum increase of RAM memory usage: %d MiB" % max_usage)


if __name__ == "__main__":
measure_memory(inference)
Loading

0 comments on commit 09ba169

Please sign in to comment.