Update README.md
Browse files
README.md
CHANGED
@@ -58,12 +58,23 @@ This repository provides all the necessary tools to perform automatic speech
|
|
58 |
recognition from an end-to-end system pretrained on LibriSpeech (EN) within
|
59 |
SpeechBrain. For a better experience, we encourage you to learn more about
|
60 |
[SpeechBrain](https://speechbrain.github.io).
|
61 |
-
The performance of the model is the following:
|
62 |
|
63 |
| Release | Test clean WER | Test other WER | GPUs |
|
64 |
|:-------------:|:--------------:|:--------------:|:--------:|
|
65 |
| 24-02-26 | 2.72 | 3.13 | 4xA100 80GB |
|
66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
## Pipeline description
|
68 |
|
69 |
TODO
|
|
|
58 |
recognition from an end-to-end system pretrained on LibriSpeech (EN) within
|
59 |
SpeechBrain. For a better experience, we encourage you to learn more about
|
60 |
[SpeechBrain](https://speechbrain.github.io).
|
61 |
+
The performance of the model in full context mode (no streaming) is the following:
|
62 |
|
63 |
| Release | Test clean WER | Test other WER | GPUs |
|
64 |
|:-------------:|:--------------:|:--------------:|:--------:|
|
65 |
| 24-02-26 | 2.72 | 3.13 | 4xA100 80GB |
|
66 |
|
67 |
+
With streaming, the results with different chunk sizes on test-clean are the following:
|
68 |
+
|
69 |
+
| | full | cs=32 (1280ms) | 24 (960ms) | 16 (640ms) | 12 (480ms) | 8 (320ms) |
|
70 |
+
|:-----:|:----:|:-----:|:-----:|:-----:|:-----:|:-----:|
|
71 |
+
| full | 2.72%| - | - | - | - | - |
|
72 |
+
| lc=32 | - | 3.09% | 3.07% | 3.26% | 3.31% | 3.44% |
|
73 |
+
| 16 | - | 3.10% | 3.07% | 3.27% | 3.32% | 3.50% |
|
74 |
+
| 8 | - | 3.10% | 3.11% | 3.31% | 3.39% | 3.62% |
|
75 |
+
| 4 | - | 3.12% | 3.13% | 3.37% | 3.51% | 3.80% |
|
76 |
+
| 2 | - | 3.19% | 3.24% | 3.50% | 3.79% | 4.38% |
|
77 |
+
|
78 |
## Pipeline description
|
79 |
|
80 |
TODO
|