mirror of
https://github.com/snakers4/silero-vad.git
synced 2026-02-05 18:09:22 +08:00
add 116 lang classifier
This commit is contained in:
adamnsandle
77
README.md
77
README.md
@@ -94,6 +94,7 @@ The models are small enough to be included directly into this repository. Newer
|
||||
| `'silero_vad_mini_8k'` | 100K | VAD | Yes | `ru`, `en`, `de`, `es` (*) | :heavy_check_mark: | :heavy_check_mark: | [](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb) |
|
||||
| `'silero_number_detector'` | 1.1M | Number Detector | No | `ru`, `en`, `de`, `es` | :heavy_check_mark: | :heavy_check_mark: | [](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb) |
|
||||
| `'silero_lang_detector'` | 1.1M | Language Classifier | No | `ru`, `en`, `de`, `es` | :heavy_check_mark: | :heavy_check_mark: | [](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb) |
|
||||
| `'silero_lang_detector_116'` | 1.7M | Language Classifier | No | [116 languages](https://github.com/snakers4/silero-vad/files/lang_dict_116.json) | :heavy_check_mark: | :heavy_check_mark: | [](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb) |
|
||||
|
||||
(*) Though explicitly trained on these languages, VAD should work on any Germanic, Romance or Slavic Languages out of the box.
|
||||
|
||||
@@ -102,6 +103,7 @@ What models do:
|
||||
- VAD - detects speech;
|
||||
- Number Detector - detects spoken numbers (i.e. thirty five);
|
||||
- Language Classifier - classifies utterances between language;
|
||||
- Language Classifier 116 - classifies among 116 languages as well as 77 language groups (mutually intelligible languages -> same group)
|
||||
|
||||
### Version History
|
||||
|
||||
@@ -116,6 +118,8 @@ What models do:
|
||||
| `v2.1` | 2021-02-11 | Add micro (10k params) VAD models |
|
||||
| `v2.2` | 2021-03-22 | Add micro 8000 sample rate VAD models |
|
||||
| `v2.3` | 2021-04-12 | Add mini (100k params) VAD models (8k and 16k sample rate) + **new** adaptive utils for full audio and single audio stream |
|
||||
| `v2.4` | 2021-07-09 | Add 116 languages classifier and group classifier
|
||||
|
|
||||
|
||||
### PyTorch
|
||||
|
||||
@@ -190,7 +194,7 @@ number_timestamps = get_number_ts(wav, model)
|
||||
pprint(number_timestamps)
|
||||
```
|
||||
|
||||
#### Language Classifier
|
||||
#### Language Classifier (4 languages)
|
||||
|
||||
[](https://pytorch.org/hub/snakers4_silero-vad_language/)
|
||||
|
||||
@@ -213,6 +217,31 @@ language = get_language(wav, model)
|
||||
pprint(language)
|
||||
```
|
||||
|
||||
#### Language Classifier (116 languages)
|
||||
|
||||
[](https://pytorch.org/hub/snakers4_silero-vad_language/)
|
||||
|
||||
```python
|
||||
import torch
|
||||
torch.set_num_threads(1)
|
||||
from pprint import pprint
|
||||
|
||||
model, lang_dict, lang_group_dict, utils = torch.hub.load(
|
||||
repo_or_dir='snakers4/silero-vad',
|
||||
model='silero_lang_detector_116',
|
||||
force_reload=True)
|
||||
|
||||
get_language_and_group, read_audio = utils
|
||||
|
||||
files_dir = torch.hub.get_dir() + '/snakers4_silero-vad_master/files'
|
||||
|
||||
wav = read_audio(f'{files_dir}/de.wav')
|
||||
language, language_group = get_language_and_group(wav, model, lang_dict, lang_group_dict)
|
||||
|
||||
pprint(f'Language: {language}')
|
||||
pprint(f'Language group: {language_group}')
|
||||
```
|
||||
|
||||
### ONNX
|
||||
|
||||
[](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb)
|
||||
@@ -296,7 +325,7 @@ number_timestamps = get_number_ts(wav, model, run_function=validate_onnx)
|
||||
pprint(number_timestamps)
|
||||
```
|
||||
|
||||
#### Language Classifier
|
||||
#### Language Classifier (4 languages)
|
||||
|
||||
```python
|
||||
import torch
|
||||
@@ -327,6 +356,44 @@ wav = read_audio(f'{files_dir}/de.wav')
|
||||
language = get_language(wav, model, run_function=validate_onnx)
|
||||
print(language)
|
||||
```
|
||||
|
||||
#### Language Classifier (116 languages)
|
||||
|
||||
```python
|
||||
import torch
|
||||
import onnxruntime
|
||||
from pprint import pprint
|
||||
|
||||
model, lang_dict, lang_group_dict, utils = torch.hub.load(
|
||||
repo_or_dir='snakers4/silero-vad',
|
||||
model='silero_lang_detector_116',
|
||||
force_reload=True)
|
||||
|
||||
get_language_and_group, read_audio = utils
|
||||
|
||||
files_dir = torch.hub.get_dir() + '/snakers4_silero-vad_master/files'
|
||||
|
||||
def init_onnx_model(model_path: str):
|
||||
return onnxruntime.InferenceSession(model_path)
|
||||
|
||||
def validate_onnx(model, inputs):
|
||||
with torch.no_grad():
|
||||
ort_inputs = {'input': inputs.cpu().numpy()}
|
||||
outs = model.run(None, ort_inputs)
|
||||
outs = [torch.Tensor(x) for x in outs]
|
||||
return outs
|
||||
|
||||
model = init_onnx_model(f'{files_dir}/lang_classifier_116.onnx')
|
||||
wav = read_audio(f'{files_dir}/de.wav')
|
||||
|
||||
language, language_group = get_language_and_group(wav, model, lang_dict, lang_group_dict)
|
||||
|
||||
pprint(f'Language: {language}')
|
||||
pprint(f'Language group: {language_group}')
|
||||
|
||||
```
|
||||
[](https://pytorch.org/hub/snakers4_silero-vad_language/)
|
||||
|
||||
## Metrics
|
||||
|
||||
### Performance Metrics
|
||||
@@ -464,6 +531,12 @@ Please see [Quality Metrics](#quality-metrics)
|
||||
- More languages TBD
|
||||
- Arbitrary audio length can be used, although network was trained using audio shorter than 15 seconds
|
||||
|
||||
### How Language Classifier 116
|
||||
|
||||
- **83%** validation accuracy among 116 languages, **87%** validation accuracy among [77 language groups](https://github.com/snakers4/silero-vad/files/lang_group_dict_116.json)
|
||||
- Language classifier 116 was trained using audio samples in [116 languages](https://github.com/snakers4/silero-vad/files/lang_dict_116.json)
|
||||
- Arbitrary audio length can be used, although network was trained using audio shorter than 20 seconds
|
||||
|
||||
## Contact
|
||||
|
||||
### Get in Touch
|
||||
|
||||
Reference in New Issue
Block a user