Update README.md

README.md

@@ -121,15 +121,15 @@ for fine-tuning.
 Whisper was proposed in the paper [Robust Speech Recognition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356) 
 by Alec Radford et al. from OpenAI. The original code repository can be found [here](https://github.com/openai/whisper).
 
-`Whisper-large-v3` has the same architecture as the previous large models except the following minor differences:
+Whisper `large-v3` has the same architecture as the previous large models except the following minor differences:
 
 1. The input uses 128 Mel frequency bins instead of 80
 2. A new language token for Cantonese
 
-The `Whisper-large-v3` model is trained on 1 million hours of weakly labeled audio and 4 million hours of pseudolabeled audio collected using `whisper-large-v2`. 
+The Whisper `large-v3` model is trained on 1 million hours of weakly labeled audio and 4 million hours of pseudolabeled audio collected using Whisper `large-v2`. 
 The model was trained for 2.0 epochs over this mixture dataset.
 
-The `Whisper-large-v3` model shows improved performance over a wide variety of languages, performs lower than 60% error rate on Common Voice 15 and Fleurs, shows 10% to 20% reduction of errors compared to `Whisper-large-v2`.
+The `large-v3` model shows improved performance over a wide variety of languages, performs lower than 60% error rate on Common Voice 15 and Fleurs, shows 10% to 20% reduction of errors compared to Whisper `large-v2`.
 
 
 **Disclaimer**: Content for this model card has partly been written by the Hugging Face team, and parts of it were 
@@ -138,7 +138,7 @@ copied and pasted from the original model card.
 ## Model details
 
 Whisper is a Transformer based encoder-decoder model, also referred to as a _sequence-to-sequence_ model. 
-It was trained on 680k hours of labelled speech data annotated using large-scale weak supervision. 
+It was trained on 1 million hours of weakly labeled audio and 4 million hours of pseudolabeled audio collected using Whisper `large-v2`.
 
 The models were trained on either English-only data or multilingual data. The English-only models were trained 
 on the task of speech recognition. The multilingual models were trained on both speech recognition and speech 
@@ -163,7 +163,7 @@ checkpoints are summarised in the following table with links to the models on th
 
 ## Usage
 
-Whisper-large-v3 is supported in Hugging Face 🤗 Transformers through the `main` branch in the Transformers repo. To run the model, first 
+Whisper `large-v3` is supported in Hugging Face 🤗 Transformers through the `main` branch in the Transformers repo. To run the model, first 
 install the Transformers library through the GitHub repo. For this example, we'll also install 🤗 Datasets to load toy 
 audio dataset from the Hugging Face Hub:
 
@@ -186,7 +186,7 @@ from datasets import load_dataset
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
-model_id = "openai/Whisper-large-v3"
+model_id = "openai/whisper-large-v3"
 
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
@@ -220,7 +220,7 @@ To transcribe a local audio file, simply pass the path to your audio file when y
 
 ### Long-Form Transcription
 
-Through Transformers Whisper-large-v3 uses a chunked algorithm to transcribe long-form audio files (> 30-seconds). In practice, this chunked long-form algorithm 
+Through Transformers Whisper uses a chunked algorithm to transcribe long-form audio files (> 30-seconds). In practice, this chunked long-form algorithm 
 is 9x faster than the sequential algorithm proposed by OpenAI in the Whisper paper (see Table 7 of the [Distil-Whisper paper](https://arxiv.org/abs/2311.00430)).
 
 To enable chunking, pass the `chunk_length_s` parameter to the `pipeline`. To activate batching, pass the argument `batch_size`:
@@ -234,7 +234,7 @@ from datasets import load_dataset
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
-model_id = "openai/Whisper-large-v3"
+model_id = "openai/whisper-large-v3"
 
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
@@ -272,7 +272,7 @@ result = pipe("https://huggingface.co/datasets/sanchit-gandhi/librispeech_long/r
 
 ### Speculative Decoding
 
-[Distil-Whisper](https://hf.co/distil-whisper/large-v2) can be used as an assistant model to Whisper for speculative decoding. Speculative decoding mathematically
+Whisper `tiny` can be used as an assistant model to Whisper for speculative decoding. Speculative decoding mathematically
 ensures the exact same outputs as Whisper are obtained while being 2 times faster. This makes it the perfect drop-in 
 replacement for existing Whisper pipelines, since the same outputs are guaranteed.
 
@@ -287,7 +287,7 @@ from datasets import load_dataset
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
-assistant_model_id = "distil-whisper/distil-large-v2"
+assistant_model_id = "openai/whisper-tiny"
 
 assistant_model = AutoModelForCausalLM.from_pretrained(
     assistant_model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
@@ -375,7 +375,7 @@ In particular, we caution against using Whisper models to transcribe recordings
 
 ## Training Data
 
-The models are trained on 680,000 hours of audio and the corresponding transcripts collected from the internet. 65% of this data (or 438,000 hours) represents English-language audio and matched English transcripts, roughly 18% (or 126,000 hours) represents non-English audio and English transcripts, while the final 17% (or 117,000 hours) represents non-English audio and the corresponding transcript. This non-English data represents 98 different languages. 
+The models are trained on 1 million hours of weakly labeled audio and 4 million hours of pseudolabeled audio collected using Whisper `large-v2`. 
 
 As discussed in [the accompanying paper](https://cdn.openai.com/papers/whisper.pdf), we see that performance on transcription in a given language is directly correlated with the amount of training data we employ in that language.