fastinom commited on
Commit
f4c509a
1 Parent(s): e1d8c4c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -44
README.md CHANGED
@@ -109,13 +109,13 @@ The following hyperparameters were used during training:
109
 
110
  | Training Loss | WER | Step | Validation Loss |
111
  |:-------------:|:-----:|:----:|:---------------:|
112
- | 6.427 | 0.33 | 200 | 0.5634 |
113
- | 0.5994 | 0.67 | 400 | 0.5290 |
114
- | 0.584 | 1.0 | 600 | 0.4924 |
115
- | 0.5589 | 1.33 | 800 | 0.4828 |
116
- | 0.5747 | 1.67 | 1000 | 0.4848 |
117
- | 0.5904 | 2.0 | 1200 | 0.4831 |
118
- |
119
 
120
 
121
 
@@ -153,15 +153,6 @@ The following hyperparameters were used during training:
153
 
154
  [More Information Needed]
155
 
156
- #### Summary
157
-
158
-
159
-
160
- ## Model Examination [optional]
161
-
162
- <!-- Relevant interpretability work for the model goes here -->
163
-
164
- [More Information Needed]
165
 
166
  ## Environmental Impact
167
 
@@ -169,11 +160,10 @@ The following hyperparameters were used during training:
169
 
170
  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
171
 
172
- - **Hardware Type:** [More Information Needed]
173
- - **Hours used:** [More Information Needed]
174
- - **Cloud Provider:** [More Information Needed]
175
- - **Compute Region:** [More Information Needed]
176
- - **Carbon Emitted:** [More Information Needed]
177
 
178
  ## Technical Specifications [optional]
179
 
@@ -193,32 +183,11 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
193
 
194
  [More Information Needed]
195
 
196
- ## Citation [optional]
197
-
198
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
199
-
200
- **BibTeX:**
201
-
202
- [More Information Needed]
203
-
204
- **APA:**
205
-
206
- [More Information Needed]
207
-
208
- ## Glossary [optional]
209
-
210
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
211
-
212
- [More Information Needed]
213
-
214
- ## More Information [optional]
215
-
216
- [More Information Needed]
217
 
218
  ## Model Card Authors [optional]
219
 
220
- [More Information Needed]
221
 
222
  ## Model Card Contact
223
 
224
- [More Information Needed]
 
109
 
110
  | Training Loss | WER | Step | Validation Loss |
111
  |:-------------:|:-----:|:----:|:---------------:|
112
+ | 6.427 | 1.00 | 200 | 4.1518 |
113
+ | 3.7979 | 1.00 | 400 | 3.8410 |
114
+ | 3.6924 | 1.00 | 600 | 3.4249 |
115
+ | 0.8357 | 0.26 | 800 | 0.2396 |
116
+ | 0.1528 | 0.24 | 1000 | 0.2155 |
117
+ | 0.1415 | 0.24 | 1200 | 0.2036 |
118
+ | 0.1278 | 0.24 | 1400 | 0.2028 |
119
 
120
 
121
 
 
153
 
154
  [More Information Needed]
155
 
 
 
 
 
 
 
 
 
 
156
 
157
  ## Environmental Impact
158
 
 
160
 
161
  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
162
 
163
+ - **Hardware Type:** [T4 GPU]
164
+ - **Hours used:** [3]
165
+ - **Cloud Provider:** [Google Colab]
166
+
 
167
 
168
  ## Technical Specifications [optional]
169
 
 
183
 
184
  [More Information Needed]
185
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
186
 
187
  ## Model Card Authors [optional]
188
 
189
+ [Fastino Mateteva]
190
 
191
  ## Model Card Contact
192
 
193
+ [fastinomateteva@gmail.com]