update model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- uz
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
- mozilla-foundation/common_voice_8_0
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
- robust-speech-event
|
| 10 |
+
datasets:
|
| 11 |
+
- mozilla-foundation/common_voice_8_0
|
| 12 |
+
model-index:
|
| 13 |
+
- name: XLS-R-300M Uzbek CV8
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: Common Voice 8
|
| 20 |
+
type: mozilla-foundation/common_voice_8_0
|
| 21 |
+
args: uz
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Test WER
|
| 24 |
+
type: wer
|
| 25 |
+
value: 40.56
|
| 26 |
+
- name: Test CER
|
| 27 |
+
type: cer
|
| 28 |
+
value: 8.25
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 32 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 33 |
+
|
| 34 |
+
# XLS-R-300M Uzbek CV8
|
| 35 |
+
|
| 36 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - UG dataset.
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
For a description of the model architecture, see [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m)
|
| 41 |
+
|
| 42 |
+
The model vocabulary consists of the [Modern Latin alphabet for Uzbek](https://en.wikipedia.org/wiki/Uzbek_alphabet), with punctuation removed.
|
| 43 |
+
Note that the characters ‘ and ’ do not count as punctuation, as ‘ modifies <o> and <g>, and ’ indicates the glottal stop.
|
| 44 |
+
|
| 45 |
+
## Intended uses & limitations
|
| 46 |
+
|
| 47 |
+
This model is expected to be of some utility for low-fidelity use cases such as:
|
| 48 |
+
- Draft video captions
|
| 49 |
+
- Indexing of recorded broadcasts
|
| 50 |
+
|
| 51 |
+
The model is not reliable enough to use as a substitute for live captions for accessibility purposes, and it should not be used in a manner that would infringe the privacy of any of the contributors to the Common Voice dataset nor any other speakers.
|
| 52 |
+
|
| 53 |
+
## Training and evaluation data
|
| 54 |
+
|
| 55 |
+
The 30% of the `train` common voice official split was used as training data. The half of the official `dev` split was used as validation data, and the full `test` set was used for final evaluation.
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
### Framework versions
|
| 59 |
+
|
| 60 |
+
- Transformers 4.17.0.dev0
|
| 61 |
+
- Pytorch 1.10.2+cu102
|
| 62 |
+
- Datasets 1.18.3
|
| 63 |
+
- Tokenizers 0.11.0
|
| 64 |
+
|