update README

README.md

@@ -49,7 +49,7 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
 LANG_ID = "fr"
 MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-french"
-SAMPLES = 5
+SAMPLES = 10
 
 test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
 
@@ -86,6 +86,11 @@ for i, predicted_sentence in enumerate(predicted_sentences):
 | "J'AI DIT QUE LES ACTEURS DE BOIS AVAIENT, SELON MOI, BEAUCOUP D'AVANTAGES SUR LES AUTRES." | JAI DIT QUE LES ACTEURS DE BOIS AVAIENT SELON MOI BEAUCOUP DAVANTAGES SUR LES AUTRES |
 | LES PAYS-BAS ONT REMPORTÉ TOUTES LES ÉDITIONS. | LE PAYS-BAS AN REMPORTAIT TOUTES LES ÉDITIONS |
 | IL Y A MAINTENANT UNE GARE ROUTIÈRE. | IL A MA ANDIN GARD DETIRON |
+| HUIT | HUIT |
+| DANS L’ATTENTE DU LENDEMAIN, ILS NE POUVAIENT SE DÉFENDRE D’UNE VIVE ÉMOTION | DANS L'ATTENTE DU LENDEMAIN IL NE POUVAIT SE DÉFENDRE D'UNE VIVE ÉMOTION |
+| LA PREMIÈRE SAISON EST COMPOSÉE DE DOUZE ÉPISODES. | LA PREMIÈRE SAISON EST COMPOSÉE DE DOUX ÉPISODES |
+| ELLE SE TROUVE ÉGALEMENT DANS LES ÎLES BRITANNIQUES. | ELLE SE TROUVE ÉGALEMENT DANS LES ÎLES BRITANNIQUES |
+| ZÉRO | ZÉRO |
 
 ## Evaluation
 
@@ -102,9 +107,11 @@ LANG_ID = "fr"
 MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-french"
 DEVICE = "cuda"
 
-CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞", 
+CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
                    "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
-                   "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。"]
+                   "{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
+                   "、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽",
+                   "『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "ʻ", "ˆ"]
 
 test_dataset = load_dataset("common_voice", LANG_ID, split="test")
 
@@ -152,11 +159,15 @@ print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_
 
 **Test Result**:
 
-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 2021-04-21). 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.
+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 2021-05-16). 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.
 
 | Model | WER | CER |
 | ------------- | ------------- | ------------- |
 | jonatasgrosman/wav2vec2-large-xlsr-53-french | **16.86%** | **5.65%** |
-| Ilyes/wav2vec2-large-xlsr-53-french | 24.76% | 8.06% |
+| Ilyes/wav2vec2-large-xlsr-53-french | 19.67% | 6.70% |
+| jonatasgrosman/wav2vec2-large-fr-voxpopuli-french | 19.80% | 6.89% |
+| Nhut/wav2vec2-large-xlsr-french | 24.09% | 8.42% |
 | facebook/wav2vec2-large-xlsr-53-french | 25.45% | 10.35% |
 | MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-French | 28.22% | 9.70% |
+| Ilyes/wav2vec2-large-xlsr-53-french_punctuation | 29.80% | 11.79% |
+| facebook/wav2vec2-base-10k-voxpopuli-ft-fr | 61.06% | 33.31% |