Update README.md

README.md

@@ -5,7 +5,7 @@ tags:
 metrics:
 - wer
 model-index:
-- name: whisper-large-v2-arabic-5k-steps
+- name: whisper-large-v2-english-2k-steps
   results: []
 datasets:
 - mozilla-foundation/common_voice_11_0
@@ -16,16 +16,13 @@ language:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# whisper-large-v2-arabic-5k-steps
+# whisper-large-v2-english-2k-steps
 
 This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the Arabic CommonVoice dataset (v11).
-It achieves the following results on the evaluation set:
-- Loss: 0.3434
-- Wer: 0.4239
 
 ## Model description
 
-This model is finetuned for 5000 steps for research purposes which means that the transcriptions might not be that satisfactory for users.
+This model is finetuned for 2000 steps for research purposes which means that the transcriptions might not be that satisfactory for users.
 
 ## Training and evaluation data
 
@@ -48,16 +45,6 @@ The following hyperparameters were used during training:
 - training_steps: 5000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.1638        | 1.78  | 1000 | 0.2295          | 0.4410 |
-| 0.0587        | 3.57  | 2000 | 0.2337          | 0.4272 |
-| 0.0125        | 5.35  | 3000 | 0.2745          | 0.4208 |
-| 0.004         | 7.13  | 4000 | 0.3124          | 0.4252 |
-| 0.0016        | 8.91  | 5000 | 0.3434          | 0.4239 |
-
 ### Transcription:
 
 ```python
@@ -69,12 +56,12 @@ from transformers import WhisperProcessor, WhisperForConditionalGeneration
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 # load the model
-processor = WhisperProcessor.from_pretrained("clu-ling/whisper-large-v2-arabic-5k-steps")
-model = WhisperForConditionalGeneration.from_pretrained("clu-ling/whisper-large-v2-arabic-5k-steps").to(device)
-forced_decoder_ids = processor.get_decoder_prompt_ids(language="ar", task="transcribe")
+processor = WhisperProcessor.from_pretrained("clu-ling/whisper-large-v2-english-2k-steps")
+model = WhisperForConditionalGeneration.from_pretrained("clu-ling/whisper-large-v2-english-2k-steps").to(device)
+forced_decoder_ids = processor.get_decoder_prompt_ids(language="en", task="transcribe")
 
 # load the dataset
-commonvoice_eval = load_dataset("mozilla-foundation/common_voice_11_0", "ar", split="validation", streaming=True)
+commonvoice_eval = load_dataset("mozilla-foundation/common_voice_11_0", "en", split="validation", streaming=True)
 commonvoice_eval = commonvoice_eval.cast_column("audio", Audio(sampling_rate=16000))
 sample = next(iter(commonvoice_eval))["audio"]
 
@@ -86,7 +73,6 @@ predicted_ids = model.generate(input_features.to(device), forced_decoder_ids=for
 transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
 
 print("Transcription:", transcription)
-Transcription: عمي هو أخو أبي.
 ```
 
 ### Evaluation:
@@ -94,7 +80,6 @@ Transcription: عمي هو أخو أبي.
 Evaluates this model on `mozilla-foundation/common_voice_11_0` test split.
 
 ```python
-import pyarabic.araby as araby
 from transformers.models.whisper.english_normalizer import BasicTextNormalizer
 from datasets import load_dataset, Audio
 import evaluate
@@ -109,40 +94,29 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 wer_metric = evaluate.load("wer")
 
 # model
-processor = WhisperProcessor.from_pretrained("clu-ling/whisper-large-v2-arabic-5k-steps")
-model = WhisperForConditionalGeneration.from_pretrained("clu-ling/whisper-large-v2-arabic-5k-steps")
+processor = WhisperProcessor.from_pretrained("clu-ling/whisper-large-v2-english-2k-steps")
+model = WhisperForConditionalGeneration.from_pretrained("clu-ling/whisper-large-v2-english-2k-steps")
 
 # dataset
-dataset = load_dataset("mozilla-foundation/common_voice_11_0", "ar", split="test", ) #cache_dir=args.cache_dir
+dataset = load_dataset("mozilla-foundation/common_voice_11_0", "en", split="test", ) #cache_dir=args.cache_dir
 dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
 
 #for debuggings: it gets two examples
 #dataset = dataset.shard(num_shards=10000, index=0)
 #print(dataset)
-
-def clean_text(text):
-  """Normalizes TRANSCRIPT"""
-  text = re.sub(r'[\,\?\.\!\-\;\:\"\“\%\٪\‘\”\�\«\»\،\.\:\؟\؛\*\>\<]', '', text) + " " # special characters
-  text = re.sub(r'http\S+', '', text) + " " # links
-  text = re.sub(r'[\[\]\(\)\-\/\{\}]', '', text) + " " # brackets
-  text = re.sub(r'\s+', ' ', text) + " " # extra white space
-  text = araby.strip_diacritics(text) # remove diacrirics
-  return text.strip()
     
 def normalize(batch):
-  """Normalizes GOLD"""
-  #batch["gold_text"] = whisper_norm(batch['sentence'])
-  batch["gold_text"] = clean_text(batch['sentence'])
+  batch["gold_text"] = whisper_norm(batch['sentence'])
   return batch
 
 def map_wer(batch):
   model.to(device)
-  forced_decoder_ids = processor.get_decoder_prompt_ids(language = "ar", task = "transcribe")
+  forced_decoder_ids = processor.get_decoder_prompt_ids(language = "en", task = "transcribe")
   inputs = processor(batch["audio"]["array"], sampling_rate=batch["audio"]["sampling_rate"], return_tensors="pt").input_features
   with torch.no_grad():
     generated_ids = model.generate(inputs=inputs.to(device), forced_decoder_ids=forced_decoder_ids)
     transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
-  batch["predicted_text"] = clean_text(transcription)
+  batch["predicted_text"] = whisper_norm(transcription)
   return batch
 
 # process GOLD text