MarieAlvenir commited on
Commit
8b23e47
·
1 Parent(s): 30f680f

Small change of reference to this model

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -182,7 +182,7 @@ The model was firstly evaluated on a tentative version of the coral-v2 conversat
182
  The results are tentative as the test set only includes 5 unique speakers, of which 4 are women.
183
  The test set includes 2 speakers with 'Fynsk' dialect, 1 with 'Sønderjysk', 1 with 'Non-native' and 1 'Nordjysk'.
184
 
185
- Note that the high generelization error on conversation data for models trained on read-aloud data is still being analyzed.
186
 
187
  | Model | Number of parameters | Finetuned on data of type | [CoRal-v2::conversation](https://huggingface.co/datasets/CoRal-project/coral-v2/viewer/conversation/test) CER | [CoRal-v2::conversation](https://huggingface.co/datasets/CoRal-project/coral-v2/viewer/conversation/test) WER |
188
  | :-------------------------------------------------------------------------------------------------- | -------------------: | --------------------------: | ------------------------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------------------------------------: |
@@ -271,7 +271,7 @@ Note that the high generelization error on conversation data for models trained
271
 
272
  <details>
273
  <summary>
274
- <b>Experiments with Røst-wav2vec2-315M with and without language model</b>
275
  </summary>
276
 
277
  The inclusion of a post-processing language model can affect the performance significantly.
@@ -283,7 +283,7 @@ Note that the high generelization error on conversation data for models trained
283
  | [CoRal-project/roest-wav2vec2-1B-v2](https://huggingface.co/CoRal-project/roest-wav2vec2-1B-v2) | 1B | Read-aloud and conversation | Yes | **6.5% ± 0.2%** | **16.4% ± 0.4%** |
284
  | [CoRal-project/roest-wav2vec2-1B-v2](https://huggingface.co/CoRal-project/roest-wav2vec2-1B-v2) | 1B | Read-aloud and conversation | No | 8.1% ± 0.2% | 23.9% ± 0.4% |
285
  | CoRal-project/roest-wav2vec2-315M-v2 (This model) | 315M | Read-aloud and conversation | Yes | **6.5% ± 0.2%** | **16.3% ± 0.4%** |
286
- | CoRal-project/roest-wav2vec2-315M-v2 (This model) | 315M | Read-aloud and conversation | No | 8.2% ± 0.2% | 25.1% ± 0.4% |
287
  | [CoRal-project/roest-wav2vec2-315m-v1](https://huggingface.co/CoRal-project/roest-wav2vec2-315m-v1) | 315M | Read-aloud | Yes | 6.6% ± 0.2% | 17.0% ± 0.4% |
288
  | [CoRal-project/roest-wav2vec2-315m-v1](https://huggingface.co/CoRal-project/roest-wav2vec2-315m-v1) | 315M | Read-aloud | No | 8.6% ± 0.2% | 26.3% ± 0.5% |
289
 
 
182
  The results are tentative as the test set only includes 5 unique speakers, of which 4 are women.
183
  The test set includes 2 speakers with 'Fynsk' dialect, 1 with 'Sønderjysk', 1 with 'Non-native' and 1 'Nordjysk'.
184
 
185
+ Note that the high generalization error on conversation data for models trained on read-aloud data is still being analyzed.
186
 
187
  | Model | Number of parameters | Finetuned on data of type | [CoRal-v2::conversation](https://huggingface.co/datasets/CoRal-project/coral-v2/viewer/conversation/test) CER | [CoRal-v2::conversation](https://huggingface.co/datasets/CoRal-project/coral-v2/viewer/conversation/test) WER |
188
  | :-------------------------------------------------------------------------------------------------- | -------------------: | --------------------------: | ------------------------------------------------------------------------------------------------------------: | ------------------------------------------------------------------------------------------------------------: |
 
271
 
272
  <details>
273
  <summary>
274
+ <b>Experiments with Røst-wav2vec2 with and without language model</b>
275
  </summary>
276
 
277
  The inclusion of a post-processing language model can affect the performance significantly.
 
283
  | [CoRal-project/roest-wav2vec2-1B-v2](https://huggingface.co/CoRal-project/roest-wav2vec2-1B-v2) | 1B | Read-aloud and conversation | Yes | **6.5% ± 0.2%** | **16.4% ± 0.4%** |
284
  | [CoRal-project/roest-wav2vec2-1B-v2](https://huggingface.co/CoRal-project/roest-wav2vec2-1B-v2) | 1B | Read-aloud and conversation | No | 8.1% ± 0.2% | 23.9% ± 0.4% |
285
  | CoRal-project/roest-wav2vec2-315M-v2 (This model) | 315M | Read-aloud and conversation | Yes | **6.5% ± 0.2%** | **16.3% ± 0.4%** |
286
+ | CoRal-project/roest-wav2vec2-315M-v2 | 315M | Read-aloud and conversation | No | 8.2% ± 0.2% | 25.1% ± 0.4% |
287
  | [CoRal-project/roest-wav2vec2-315m-v1](https://huggingface.co/CoRal-project/roest-wav2vec2-315m-v1) | 315M | Read-aloud | Yes | 6.6% ± 0.2% | 17.0% ± 0.4% |
288
  | [CoRal-project/roest-wav2vec2-315m-v1](https://huggingface.co/CoRal-project/roest-wav2vec2-315m-v1) | 315M | Read-aloud | No | 8.6% ± 0.2% | 26.3% ± 0.5% |
289