Get back to checkpoint 17000 and modify readme
Browse files- README.md +5 -16
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -6,32 +6,20 @@ tags:
|
|
| 6 |
- automatic-speech-recognition
|
| 7 |
- mozilla-foundation/common_voice_8_0
|
| 8 |
- generated_from_trainer
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: ''
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 14 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
-
|
| 17 |
-
#
|
| 18 |
-
|
| 19 |
-
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 - FR dataset.
|
| 20 |
-
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: inf
|
| 22 |
-
- Wer: 0.9997
|
| 23 |
-
|
| 24 |
## Model description
|
| 25 |
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
## Intended uses & limitations
|
| 29 |
-
|
| 30 |
-
More information needed
|
| 31 |
|
| 32 |
## Training and evaluation data
|
| 33 |
|
| 34 |
-
|
|
|
|
| 35 |
|
| 36 |
## Training procedure
|
| 37 |
|
|
@@ -72,6 +60,7 @@ The following hyperparameters were used during training:
|
|
| 72 |
| 0.8488 | 4.59 | 16000 | inf | 0.2187 |
|
| 73 |
| 0.8359 | 4.87 | 17000 | inf | 0.2172 |
|
| 74 |
|
|
|
|
| 75 |
|
| 76 |
### Framework versions
|
| 77 |
|
|
|
|
| 6 |
- automatic-speech-recognition
|
| 7 |
- mozilla-foundation/common_voice_8_0
|
| 8 |
- generated_from_trainer
|
| 9 |
+
- robust-speech-event
|
| 10 |
model-index:
|
| 11 |
- name: ''
|
| 12 |
results: []
|
| 13 |
---
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
## Model description
|
| 16 |
|
| 17 |
+
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 - FR dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Training and evaluation data
|
| 20 |
|
| 21 |
+
It achieves the following results on the evaluation set (Step 17000):
|
| 22 |
+
- Wer: 0.2172
|
| 23 |
|
| 24 |
## Training procedure
|
| 25 |
|
|
|
|
| 60 |
| 0.8488 | 4.59 | 16000 | inf | 0.2187 |
|
| 61 |
| 0.8359 | 4.87 | 17000 | inf | 0.2172 |
|
| 62 |
|
| 63 |
+
Got some issue with validation loss calculation.
|
| 64 |
|
| 65 |
### Framework versions
|
| 66 |
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262112241
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c1f086a24d555df97dfb5f6d946142c487382a19b667581f20596eb7a64346a
|
| 3 |
size 1262112241
|