Plim commited on
Commit
5b2ae7b
2 Parent(s): 1f7860a f804256

Merge branch 'main' of https://huggingface.co/Plim/xls-r-300m-cv_8-fr into main

Browse files
Files changed (1) hide show
  1. README.md +16 -5
README.md CHANGED
@@ -44,11 +44,6 @@ model-index:
44
 
45
  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.
46
 
47
- ## Training and evaluation data
48
-
49
- It achieves the following results on the evaluation set (Step 17000):
50
- - Wer: 0.2172
51
-
52
  ## Training procedure
53
 
54
  ### Training hyperparameters
@@ -88,6 +83,9 @@ The following hyperparameters were used during training:
88
  | 0.8488 | 4.59 | 16000 | inf | 0.2187 |
89
  | 0.8359 | 4.87 | 17000 | inf | 0.2172 |
90
 
 
 
 
91
  Got some issue with validation loss calculation.
92
 
93
  ### Framework versions
@@ -96,3 +94,16 @@ Got some issue with validation loss calculation.
96
  - Pytorch 1.10.2+cu102
97
  - Datasets 1.18.3.dev0
98
  - Tokenizers 0.11.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
 
45
  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.
46
 
 
 
 
 
 
47
  ## Training procedure
48
 
49
  ### Training hyperparameters
 
83
  | 0.8488 | 4.59 | 16000 | inf | 0.2187 |
84
  | 0.8359 | 4.87 | 17000 | inf | 0.2172 |
85
 
86
+ It achieves the best result on the validation set on Step 17000:
87
+ - Wer: 0.2172
88
+
89
  Got some issue with validation loss calculation.
90
 
91
  ### Framework versions
 
94
  - Pytorch 1.10.2+cu102
95
  - Datasets 1.18.3.dev0
96
  - Tokenizers 0.11.0
97
+
98
+ ### Evaluation Commands
99
+ 1. To evaluate on `mozilla-foundation/common_voice_8` with split `test`
100
+
101
+ ```bash
102
+ python eval.py --model_id Plim/xls-r-300m-cv_8-fr --dataset mozilla-foundation/common_voice_8_0 --config fr --split test
103
+ ```
104
+
105
+ 2. To evaluate on `speech-recognition-community-v2/dev_data`
106
+
107
+ ```bash
108
+ python eval.py --model_id Plim/xls-r-300m-cv_8-fr --dataset speech-recognition-community-v2/dev_data --config fr --split validation --chunk_length_s 5.0 --stride_length_s 1.0
109
+ ```