harshit345 commited on
Commit
0ab6992
·
1 Parent(s): e6cc099

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -13
README.md CHANGED
@@ -35,9 +35,8 @@ model-index:
35
  Fine-tuned [facebook/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on English using the [Common Voice](https://huggingface.co/datasets/common_voice).
36
  When using this model, make sure that your speech input is sampled at 16kHz.
37
 
38
- This model has been fine-tuned thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :)
39
 
40
- The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
41
 
42
  ## Usage
43
 
@@ -174,18 +173,13 @@ print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_
174
 
175
  **Test Result**:
176
 
177
- In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the evaluation script described above on other models as well (on 2021-06-17). Note that the table below may show different results from those already reported, this may have been caused due to some specificity of the other evaluation scripts used.
178
 
179
  | Model | WER | CER |
180
  | ------------- | ------------- | ------------- |
181
- | jonatasgrosman/wav2vec2-large-xlsr-53-english | **18.98%** | **8.29%** |
182
- | jonatasgrosman/wav2vec2-large-english | 21.53% | 9.66% |
 
183
  | facebook/wav2vec2-large-960h-lv60-self | 22.03% | 10.39% |
184
- | facebook/wav2vec2-large-960h-lv60 | 23.97% | 11.14% |
185
- | boris/xlsr-en-punctuation | 29.10% | 10.75% |
186
- | facebook/wav2vec2-large-960h | 32.79% | 16.03% |
187
- | facebook/wav2vec2-base-960h | 39.86% | 19.89% |
188
- | facebook/wav2vec2-base-100h | 51.06% | 25.06% |
189
- | elgeish/wav2vec2-large-lv60-timit-asr | 59.96% | 34.28% |
190
- | facebook/wav2vec2-base-10k-voxpopuli-ft-en | 66.41% | 36.76% |
191
- | elgeish/wav2vec2-base-timit-asr | 68.78% | 36.81% |
 
35
  Fine-tuned [facebook/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on English using the [Common Voice](https://huggingface.co/datasets/common_voice).
36
  When using this model, make sure that your speech input is sampled at 16kHz.
37
 
 
38
 
39
+
40
 
41
  ## Usage
42
 
 
173
 
174
  **Test Result**:
175
 
176
+ In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the evaluation script described above on other models as well. Note that the table below may show different results from those already reported, this may have been caused due to some specificity of the other evaluation scripts used.
177
 
178
  | Model | WER | CER |
179
  | ------------- | ------------- | ------------- |
180
+ | hkatyal345/wav2vec2-large-xlsr-53-english | **18.98%** | **8.29%** |
181
+ | hkatyal345/wav2vec2-large-xlsr-hindi | 20.01% | 9.66% |
182
+ | hkatyal345/wav2vec2-large-english | 22.00% | 9.66% |
183
  | facebook/wav2vec2-large-960h-lv60-self | 22.03% | 10.39% |
184
+ | facebook/wav2vec2-base-100h-lv60 | 24.97% | 11.14% |
185
+ |