Merge branch 'main' of https://huggingface.co/speechbrain/asr-crdnn-commonvoice-it into main
Browse files- README.md +14 -13
- example-it.wav +0 -0
README.md
CHANGED
@@ -2,13 +2,14 @@
|
|
2 |
language: "it"
|
3 |
thumbnail:
|
4 |
tags:
|
5 |
-
-
|
6 |
- CTC
|
7 |
- Attention
|
8 |
- pytorch
|
|
|
9 |
license: "apache-2.0"
|
10 |
datasets:
|
11 |
-
-
|
12 |
metrics:
|
13 |
- wer
|
14 |
- cer
|
@@ -18,7 +19,7 @@ metrics:
|
|
18 |
|
19 |
This repository provides all the necessary tools to perform automatic speech
|
20 |
recognition from an end-to-end system pretrained on CommonVoice (IT) within
|
21 |
-
SpeechBrain. For a better experience we encourage you to learn more about
|
22 |
[SpeechBrain](https://speechbrain.github.io). The given ASR model performance are:
|
23 |
|
24 |
| Release | Test CER | Test WER | GPUs |
|
@@ -27,19 +28,19 @@ SpeechBrain. For a better experience we encourage you to learn more about
|
|
27 |
|
28 |
## Pipeline description
|
29 |
|
30 |
-
This ASR system is composed
|
31 |
1. Tokenizer (unigram) that transforms words into subword units and trained with
|
32 |
the train transcriptions (train.tsv) of CommonVoice (IT).
|
33 |
-
|
34 |
-
N blocks of convolutional neural networks with
|
35 |
frequency domain. Then, a bidirectional LSTM is connected to a final DNN to obtain
|
36 |
the final acoustic representation that is given to the CTC and attention decoders.
|
37 |
|
38 |
## Intended uses & limitations
|
39 |
|
40 |
-
This model has been
|
41 |
for the Italian language. Thanks to the flexibility of SpeechBrain, any of the 2 blocks
|
42 |
-
detailed above can be extracted and connected to
|
43 |
installed.
|
44 |
|
45 |
## Install SpeechBrain
|
@@ -47,19 +48,19 @@ installed.
|
|
47 |
First of all, please install SpeechBrain with the following command:
|
48 |
|
49 |
```
|
50 |
-
pip install
|
51 |
```
|
52 |
|
53 |
Please notice that we encourage you to read our tutorials and learn more about
|
54 |
[SpeechBrain](https://speechbrain.github.io).
|
55 |
|
56 |
-
### Transcribing your own audio files
|
57 |
|
58 |
```python
|
59 |
from speechbrain.pretrained import EncoderDecoderASR
|
60 |
|
61 |
-
asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-crdnn-commonvoice-it")
|
62 |
-
asr_model.transcribe_file("
|
63 |
|
64 |
```
|
65 |
|
@@ -72,6 +73,6 @@ asr_model.transcribe_file("path_to_your_file.wav")
|
|
72 |
year = {2021},
|
73 |
publisher = {GitHub},
|
74 |
journal = {GitHub repository},
|
75 |
-
howpublished = {
|
76 |
}
|
77 |
```
|
|
|
2 |
language: "it"
|
3 |
thumbnail:
|
4 |
tags:
|
5 |
+
- automatic-speech-recognition
|
6 |
- CTC
|
7 |
- Attention
|
8 |
- pytorch
|
9 |
+
- speechbrain
|
10 |
license: "apache-2.0"
|
11 |
datasets:
|
12 |
+
- common_voice
|
13 |
metrics:
|
14 |
- wer
|
15 |
- cer
|
|
|
19 |
|
20 |
This repository provides all the necessary tools to perform automatic speech
|
21 |
recognition from an end-to-end system pretrained on CommonVoice (IT) within
|
22 |
+
SpeechBrain. For a better experience, we encourage you to learn more about
|
23 |
[SpeechBrain](https://speechbrain.github.io). The given ASR model performance are:
|
24 |
|
25 |
| Release | Test CER | Test WER | GPUs |
|
|
|
28 |
|
29 |
## Pipeline description
|
30 |
|
31 |
+
This ASR system is composed of 2 different but linked blocks:
|
32 |
1. Tokenizer (unigram) that transforms words into subword units and trained with
|
33 |
the train transcriptions (train.tsv) of CommonVoice (IT).
|
34 |
+
2. Acoustic model (CRDNN + CTC/Attention). The CRDNN architecture is made of
|
35 |
+
N blocks of convolutional neural networks with normalization and pooling on the
|
36 |
frequency domain. Then, a bidirectional LSTM is connected to a final DNN to obtain
|
37 |
the final acoustic representation that is given to the CTC and attention decoders.
|
38 |
|
39 |
## Intended uses & limitations
|
40 |
|
41 |
+
This model has been primarily developed to be run within SpeechBrain as a pretrained ASR model
|
42 |
for the Italian language. Thanks to the flexibility of SpeechBrain, any of the 2 blocks
|
43 |
+
detailed above can be extracted and connected to your custom pipeline as long as SpeechBrain is
|
44 |
installed.
|
45 |
|
46 |
## Install SpeechBrain
|
|
|
48 |
First of all, please install SpeechBrain with the following command:
|
49 |
|
50 |
```
|
51 |
+
pip install speechbrain
|
52 |
```
|
53 |
|
54 |
Please notice that we encourage you to read our tutorials and learn more about
|
55 |
[SpeechBrain](https://speechbrain.github.io).
|
56 |
|
57 |
+
### Transcribing your own audio files (in Italian)
|
58 |
|
59 |
```python
|
60 |
from speechbrain.pretrained import EncoderDecoderASR
|
61 |
|
62 |
+
asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-crdnn-commonvoice-it", savedir="pretrained_models/asr-crdnn-commonvoice-it")
|
63 |
+
asr_model.transcribe_file("speechbrain/asr-crdnn-commonvoice-it/example-it.wav")
|
64 |
|
65 |
```
|
66 |
|
|
|
73 |
year = {2021},
|
74 |
publisher = {GitHub},
|
75 |
journal = {GitHub repository},
|
76 |
+
howpublished = {\\url{https://github.com/speechbrain/speechbrain}},
|
77 |
}
|
78 |
```
|
example-it.wav
ADDED
Binary file (136 kB). View file
|
|