Hugging Face's logo

jonatasgrosman
/
wav2vec2-large-english

Automatic Speech Recognition
Transformers
PyTorch
English
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results
Inference Endpoints
Model card Files Community
1
jonatasgrosman commited on
Commit
80b0407
•
1 Parent(s): cdf0d7f

update model

Browse files
Files changed (2) hide show
  1. README.md +8 -8
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -24,10 +24,10 @@ model-index:
24
  metrics:
25
  - name: Test WER
26
  type: wer
27
- value: 21.91
28
  - name: Test CER
29
  type: cer
30
- value: 9.88
31
  ---
32
 
33
  # Wav2vec2-Large-English
@@ -81,15 +81,15 @@ for i, predicted_sentence in enumerate(predicted_sentences):
81
 
82
  | Reference | Prediction |
83
  | ------------- | ------------- |
84
- | "SHE'LL BE ALL RIGHT." | GIN BE ALL RIGHT |
85
  | SIX | SIX |
86
  | "ALL'S WELL THAT ENDS WELL." | ALL IS WELL THAT ENDS WELL |
87
- | DO YOU MEAN IT? | DO YOU REAN IT |
88
  | THE NEW PATCH IS LESS INVASIVE THAN THE OLD ONE, BUT STILL CAUSES REGRESSIONS. | THE NEW PATCH IS LESS INVASIVE THAN THE OLD ONE BUT STILL CAUSES REGRESSION |
89
- | HOW IS MOZILLA GOING TO HANDLE AMBIGUITIES LIKE QUEUE AND CUE? | HOW IS MOSTULA GOING TO BANDLE AND BE HOOT IS LIKE U AND QU |
90
- | "I GUESS YOU MUST THINK I'M KINDA BATTY." | WOSTION IS IN AN ON THE PLOTC |
91
  | NO ONE NEAR THE REMOTE MACHINE YOU COULD RING? | NO ONE NEAR THE REMOTE MACHINE YOU COULD RING |
92
- | SAUCE FOR THE GOOSE IS SAUCE FOR THE GANDER. | SAUCE FOR THE GOOSE IS SAUCE FOR THE GONDER |
93
  | GROVES STARTED WRITING SONGS WHEN SHE WAS FOUR YEARS OLD. | GRAFFES STORTED WRITING SONGS WHEN SHE WAS FOUR YEARS OLD |
94
 
95
  ## Evaluation
@@ -163,7 +163,7 @@ In the table below I report the Word Error Rate (WER) and the Character Error Ra
163
 
164
  | Model | WER | CER |
165
  | ------------- | ------------- | ------------- |
166
- | jonatasgrosman/wav2vec2-large-english | **21.91%** | **9.88%** |
167
  | facebook/wav2vec2-large-960h-lv60-self | 22.03% | 10.39% |
168
  | facebook/wav2vec2-large-960h-lv60 | 23.97% | 11.14% |
169
  | facebook/wav2vec2-large-960h | 32.79% | 16.03% |
 
24
  metrics:
25
  - name: Test WER
26
  type: wer
27
+ value: 21.16
28
  - name: Test CER
29
  type: cer
30
+ value: 9.53
31
  ---
32
 
33
  # Wav2vec2-Large-English
 
81
 
82
  | Reference | Prediction |
83
  | ------------- | ------------- |
84
+ | "SHE'LL BE ALL RIGHT." | SHE'D BE AL RIGHT |
85
  | SIX | SIX |
86
  | "ALL'S WELL THAT ENDS WELL." | ALL IS WELL THAT ENDS WELL |
87
+ | DO YOU MEAN IT? | DO YOU MEAN IT |
88
  | THE NEW PATCH IS LESS INVASIVE THAN THE OLD ONE, BUT STILL CAUSES REGRESSIONS. | THE NEW PATCH IS LESS INVASIVE THAN THE OLD ONE BUT STILL CAUSES REGRESSION |
89
+ | HOW IS MOZILLA GOING TO HANDLE AMBIGUITIES LIKE QUEUE AND CUE? | HOW IS MOSTYURLA GOING TO BANDO AMBIHOTIS LIKE YU AND Q |
90
+ | "I GUESS YOU MUST THINK I'M KINDA BATTY." | QUESTIONS IN CANTON TE PARC |
91
  | NO ONE NEAR THE REMOTE MACHINE YOU COULD RING? | NO ONE NEAR THE REMOTE MACHINE YOU COULD RING |
92
+ | SAUCE FOR THE GOOSE IS SAUCE FOR THE GANDER. | SAUCE FOR THE GOICE IS SAUCE FOR THE GONDER |
93
  | GROVES STARTED WRITING SONGS WHEN SHE WAS FOUR YEARS OLD. | GRAFFES STORTED WRITING SONGS WHEN SHE WAS FOUR YEARS OLD |
94
 
95
  ## Evaluation
 
163
 
164
  | Model | WER | CER |
165
  | ------------- | ------------- | ------------- |
166
+ | jonatasgrosman/wav2vec2-large-english | **21.16%** | **9.53%** |
167
  | facebook/wav2vec2-large-960h-lv60-self | 22.03% | 10.39% |
168
  | facebook/wav2vec2-large-960h-lv60 | 23.97% | 11.14% |
169
  | facebook/wav2vec2-large-960h | 32.79% | 16.03% |
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a1d6c543fd8f0ed1f162fd386c249a90caeaa8bfe7bee367f27f20800e8c743
3
  size 1262022892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a299003920a2ebacc857bf3f0c2706c06cc88e6c45924e4aa4cb5b9fb0c04d
3
  size 1262022892