Update README.md

README.md

@@ -1,199 +1,453 @@
 ---
-library_name: transformers
-tags: []
+language:
+- en
+- zh
+- de
+- es
+- ru
+- ko
+- fr
+- ja
+- pt
+- tr
+- pl
+- ca
+- nl
+- ar
+- sv
+- it
+- id
+- hi
+- fi
+- vi
+- he
+- uk
+- el
+- ms
+- cs
+- ro
+- da
+- hu
+- ta
+- 'no'
+- th
+- ur
+- hr
+- bg
+- lt
+- la
+- mi
+- ml
+- cy
+- sk
+- te
+- fa
+- lv
+- bn
+- sr
+- az
+- sl
+- kn
+- et
+- mk
+- br
+- eu
+- is
+- hy
+- ne
+- mn
+- bs
+- kk
+- sq
+- sw
+- gl
+- mr
+- pa
+- si
+- km
+- sn
+- yo
+- so
+- af
+- oc
+- ka
+- be
+- tg
+- sd
+- gu
+- am
+- yi
+- lo
+- uz
+- fo
+- ht
+- ps
+- tk
+- nn
+- mt
+- sa
+- lb
+- my
+- bo
+- tl
+- mg
+- as
+- tt
+- haw
+- ln
+- ha
+- ba
+- jw
+- su
+tags:
+- audio
+- automatic-speech-recognition
+- hf-asr-leaderboard
+widget:
+- example_title: Librispeech sample 1
+  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
+- example_title: Librispeech sample 2
+  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
+model-index:
+- name: whisper-small
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: LibriSpeech (clean)
+      type: librispeech_asr
+      config: clean
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 3.432213777886737
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: LibriSpeech (other)
+      type: librispeech_asr
+      config: other
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 7.628304527060248
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 11.0
+      type: mozilla-foundation/common_voice_11_0
+      config: hi
+      split: test
+      args:
+        language: hi
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 87.3
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 13.0
+      type: mozilla-foundation/common_voice_13_0
+      config: dv
+      split: test
+      args:
+        language: dv
+    metrics:
+    - name: Wer
+      type: wer
+      value: 125.69809089960707
+pipeline_tag: automatic-speech-recognition
+license: apache-2.0
+base_model:
+- openai/whisper-small
 ---
 
-# Model Card for Model ID
+# Whisper
 
-<!-- Provide a quick summary of what the model is/does. -->
+Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours 
+of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need 
+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).
 
+**Disclaimer**: Content for this model card has partly been written by the Hugging Face team, and parts of it were 
+copied and pasted from the original model card.
 
-## Model Details
+## Model details
 
-### Model Description
+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. 
 
-<!-- Provide a longer summary of what this model is. -->
+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 
+translation. For speech recognition, the model predicts transcriptions in the *same* language as the audio. 
+For speech translation, the model predicts transcriptions to a *different* language to the audio.
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+Whisper checkpoints come in five configurations of varying model sizes.
+The smallest four are trained on either English-only or multilingual data.
+The largest checkpoints are multilingual only. All ten of the pre-trained checkpoints 
+are available on the [Hugging Face Hub](https://huggingface.co/models?search=openai/whisper). The 
+checkpoints are summarised in the following table with links to the models on the Hub:
+
+| Size     | Parameters | English-only                                         | Multilingual                                        |
+|----------|------------|------------------------------------------------------|-----------------------------------------------------|
+| tiny     | 39 M       | [✓](https://huggingface.co/openai/whisper-tiny.en)   | [✓](https://huggingface.co/openai/whisper-tiny)     |
+| base     | 74 M       | [✓](https://huggingface.co/openai/whisper-base.en)   | [✓](https://huggingface.co/openai/whisper-base)     |
+| small    | 244 M      | [✓](https://huggingface.co/openai/whisper-small.en)  | [✓](https://huggingface.co/openai/whisper-small)    |
+| medium   | 769 M      | [✓](https://huggingface.co/openai/whisper-medium.en) | [✓](https://huggingface.co/openai/whisper-medium)   |
+| large    | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large)    |
+| large-v2 | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large-v2) |
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+# Usage
 
-### Model Sources [optional]
+To transcribe audio samples, the model has to be used alongside a [`WhisperProcessor`](https://huggingface.co/docs/transformers/model_doc/whisper#transformers.WhisperProcessor).
 
-<!-- Provide the basic links for the model. -->
+The `WhisperProcessor` is used to:
+1. Pre-process the audio inputs (converting them to log-Mel spectrograms for the model)
+2. Post-process the model outputs (converting them from tokens to text)
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
+The model is informed of which task to perform (transcription or translation) by passing the appropriate "context tokens". These context tokens 
+are a sequence of tokens that are given to the decoder at the start of the decoding process, and take the following order:
+1. The transcription always starts with the `<|startoftranscript|>` token
+2. The second token is the language token (e.g. `<|en|>` for English)
+3. The third token is the "task token". It can take one of two values: `<|transcribe|>` for speech recognition or `<|translate|>` for speech translation
+4. In addition, a `<|notimestamps|>` token is added if the model should not include timestamp prediction
+
+Thus, a typical sequence of context tokens might look as follows:
+```
+<|startoftranscript|> <|en|> <|transcribe|> <|notimestamps|>
+```
+Which tells the model to decode in English, under the task of speech recognition, and not to predict timestamps.
+
+These tokens can either be forced or un-forced. If they are forced, the model is made to predict each token at 
+each position. This allows one to control the output language and task for the Whisper model. If they are un-forced, 
+the Whisper model will automatically predict the output langauge and task itself.
+
+The context tokens can be set accordingly:
+
+```python
+model.config.forced_decoder_ids = WhisperProcessor.get_decoder_prompt_ids(language="english", task="transcribe")
+```
+
+Which forces the model to predict in English under the task of speech recognition.
+
+## Transcription
+
+### English to English 
+In this example, the context tokens are 'unforced', meaning the model automatically predicts the output language
+(English) and task (transcribe).
+
+```python
+>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
+>>> from datasets import load_dataset
+
+>>> # load model and processor
+>>> processor = WhisperProcessor.from_pretrained("openai/whisper-small")
+>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")
+>>> model.config.forced_decoder_ids = None
+
+>>> # load dummy dataset and read audio files
+>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+>>> sample = ds[0]["audio"]
+>>> input_features = processor(sample["array"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features 
+
+>>> # generate token ids
+>>> predicted_ids = model.generate(input_features)
+>>> # decode token ids to text
+>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
+['<|startoftranscript|><|en|><|transcribe|><|notimestamps|> Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.<|endoftext|>']
+
+>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+[' Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.']
+```
+The context tokens can be removed from the start of the transcription by setting `skip_special_tokens=True`.
+
+### French to French 
+The following example demonstrates French to French transcription by setting the decoder ids appropriately. 
+
+```python
+>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
+>>> from datasets import Audio, load_dataset
+
+>>> # load model and processor
+>>> processor = WhisperProcessor.from_pretrained("openai/whisper-small")
+>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")
+>>> forced_decoder_ids = processor.get_decoder_prompt_ids(language="french", task="transcribe")
+
+>>> # load streaming dataset and read first audio sample
+>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
+>>> ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
+>>> input_speech = next(iter(ds))["audio"]
+>>> input_features = processor(input_speech["array"], sampling_rate=input_speech["sampling_rate"], return_tensors="pt").input_features
+
+>>> # generate token ids
+>>> predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids)
+>>> # decode token ids to text
+>>> transcription = processor.batch_decode(predicted_ids)
+['<|startoftranscript|><|fr|><|transcribe|><|notimestamps|> Un vrai travail intéressant va enfin être mené sur ce sujet.<|endoftext|>']
+
+>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+[' Un vrai travail intéressant va enfin être mené sur ce sujet.']
+```
+
+## Translation 
+Setting the task to "translate" forces the Whisper model to perform speech translation.
+
+### French to English
+
+```python
+>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
+>>> from datasets import Audio, load_dataset
+
+>>> # load model and processor
+>>> processor = WhisperProcessor.from_pretrained("openai/whisper-small")
+>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")
+>>> forced_decoder_ids = processor.get_decoder_prompt_ids(language="french", task="translate")
+
+>>> # load streaming dataset and read first audio sample
+>>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
+>>> ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
+>>> input_speech = next(iter(ds))["audio"]
+>>> input_features = processor(input_speech["array"], sampling_rate=input_speech["sampling_rate"], return_tensors="pt").input_features
+
+>>> # generate token ids
+>>> predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids)
+>>> # decode token ids to text
+>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+[' A very interesting work, we will finally be given on this subject.']
+```
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
+This code snippet shows how to evaluate Whisper Small on [LibriSpeech test-clean](https://huggingface.co/datasets/librispeech_asr):
+ 
+```python
+>>> from datasets import load_dataset
+>>> from transformers import WhisperForConditionalGeneration, WhisperProcessor
+>>> import torch
+>>> from evaluate import load
 
-### Results
+>>> librispeech_test_clean = load_dataset("librispeech_asr", "clean", split="test")
 
-[More Information Needed]
+>>> processor = WhisperProcessor.from_pretrained("openai/whisper-small")
+>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small").to("cuda")
 
-#### Summary
+>>> def map_to_pred(batch):
+>>>     audio = batch["audio"]
+>>>     input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features
+>>>     batch["reference"] = processor.tokenizer._normalize(batch['text'])
+>>> 
+>>>     with torch.no_grad():
+>>>         predicted_ids = model.generate(input_features.to("cuda"))[0]
+>>>     transcription = processor.decode(predicted_ids)
+>>>     batch["prediction"] = processor.tokenizer._normalize(transcription)
+>>>     return batch
 
+>>> result = librispeech_test_clean.map(map_to_pred)
 
+>>> wer = load("wer")
+>>> print(100 * wer.compute(references=result["reference"], predictions=result["prediction"]))
+3.432213777886737
+```
 
-## Model Examination [optional]
+## Long-Form Transcription
 
-<!-- Relevant interpretability work for the model goes here -->
+The Whisper model is intrinsically designed to work on audio samples of up to 30s in duration. However, by using a chunking 
+algorithm, it can be used to transcribe audio samples of up to arbitrary length. This is possible through Transformers 
+[`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline) 
+method. Chunking is enabled by setting `chunk_length_s=30` when instantiating the pipeline. With chunking enabled, the pipeline 
+can be run with batched inference. It can also be extended to predict sequence level timestamps by passing `return_timestamps=True`:
 
-[More Information Needed]
+```python
+>>> import torch
+>>> from transformers import pipeline
+>>> from datasets import load_dataset
 
-## Environmental Impact
+>>> device = "cuda:0" if torch.cuda.is_available() else "cpu"
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+>>> pipe = pipeline(
+>>>   "automatic-speech-recognition",
+>>>   model="openai/whisper-small",
+>>>   chunk_length_s=30,
+>>>   device=device,
+>>> )
 
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+>>> sample = ds[0]["audio"]
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+>>> prediction = pipe(sample.copy(), batch_size=8)["text"]
+" Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel."
 
-## Technical Specifications [optional]
+>>> # we can also return timestamps for the predictions
+>>> prediction = pipe(sample.copy(), batch_size=8, return_timestamps=True)["chunks"]
+[{'text': ' Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.',
+  'timestamp': (0.0, 5.44)}]
+```
 
-### Model Architecture and Objective
+Refer to the blog post [ASR Chunking](https://huggingface.co/blog/asr-chunking) for more details on the chunking algorithm.
 
-[More Information Needed]
+## Fine-Tuning
 
-### Compute Infrastructure
+The pre-trained Whisper model demonstrates a strong ability to generalise to different datasets and domains. However, 
+its predictive capabilities can be improved further for certain languages and tasks through *fine-tuning*. The blog 
+post [Fine-Tune Whisper with 🤗 Transformers](https://huggingface.co/blog/fine-tune-whisper) provides a step-by-step 
+guide to fine-tuning the Whisper model with as little as 5 hours of labelled data.
 
-[More Information Needed]
+### Evaluated Use
 
-#### Hardware
+The primary intended users of these models are AI researchers studying robustness, generalization, capabilities, biases, and constraints of the current model. However, Whisper is also potentially quite useful as an ASR solution for developers, especially for English speech recognition. We recognize that once models are released, it is impossible to restrict access to only “intended” uses or to draw reasonable guidelines around what is or is not research.
 
-[More Information Needed]
+The models are primarily trained and evaluated on ASR and speech translation to English tasks. They show strong ASR results in ~10 languages. They may exhibit additional capabilities, particularly if fine-tuned on certain tasks like voice activity detection, speaker classification, or speaker diarization but have not been robustly evaluated in these areas. We strongly recommend that users perform robust evaluations of the models in a particular context and domain before deploying them.
 
-#### Software
+In particular, we caution against using Whisper models to transcribe recordings of individuals taken without their consent or purporting to use these models for any kind of subjective classification. We recommend against use in high-risk domains like decision-making contexts, where flaws in accuracy can lead to pronounced flaws in outcomes. The models are intended to transcribe and translate speech, use of the model for classification is not only not evaluated but also not appropriate, particularly to infer human attributes.
 
-[More Information Needed]
 
-## Citation [optional]
+## Training Data
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+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. 
 
-**BibTeX:**
+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.
 
-[More Information Needed]
 
-**APA:**
+## Performance and Limitations
 
-[More Information Needed]
+Our studies show that, over many existing ASR systems, the models exhibit improved robustness to accents, background noise, technical language, as well as zero shot translation from multiple languages into English; and that accuracy on speech recognition and translation is near the state-of-the-art level. 
 
-## Glossary [optional]
+However, because the models are trained in a weakly supervised manner using large-scale noisy data, the predictions may include texts that are not actually spoken in the audio input (i.e. hallucination). We hypothesize that this happens because, given their general knowledge of language, the models combine trying to predict the next word in audio with trying to transcribe the audio itself.
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+Our models perform unevenly across languages, and we observe lower accuracy on low-resource and/or low-discoverability languages or languages where we have less training data. The models also exhibit disparate performance on different accents and dialects of particular languages, which may include higher word error rate across speakers of different genders, races, ages, or other demographic criteria. Our full evaluation results are presented in [the paper accompanying this release](https://cdn.openai.com/papers/whisper.pdf). 
 
-[More Information Needed]
+In addition, the sequence-to-sequence architecture of the model makes it prone to generating repetitive texts, which can be mitigated to some degree by beam search and temperature scheduling but not perfectly. Further analysis on these limitations are provided in [the paper](https://cdn.openai.com/papers/whisper.pdf). It is likely that this behavior and hallucinations may be worse on lower-resource and/or lower-discoverability languages.
 
-## More Information [optional]
 
-[More Information Needed]
+## Broader Implications
 
-## Model Card Authors [optional]
+We anticipate that Whisper models’ transcription capabilities may be used for improving accessibility tools. While Whisper models cannot be used for real-time transcription out of the box – their speed and size suggest that others may be able to build applications on top of them that allow for near-real-time speech recognition and translation. The real value of beneficial applications built on top of Whisper models suggests that the disparate performance of these models may have real economic implications.
 
-[More Information Needed]
+There are also potential dual use concerns that come with releasing Whisper. While we hope the technology will be used primarily for beneficial purposes, making ASR technology more accessible could enable more actors to build capable surveillance technologies or scale up existing surveillance efforts, as the speed and accuracy allow for affordable automatic transcription and translation of large volumes of audio communication. Moreover, these models may have some capabilities to recognize specific individuals out of the box, which in turn presents safety concerns related both to dual use and disparate performance. In practice, we expect that the cost of transcription is not the limiting factor of scaling up surveillance projects.
 
-## Model Card Contact
 
-[More Information Needed]
+### BibTeX entry and citation info
+```bibtex
+@misc{radford2022whisper,
+  doi = {10.48550/ARXIV.2212.04356},
+  url = {https://arxiv.org/abs/2212.04356},
+  author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
+  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
+  publisher = {arXiv},
+  year = {2022},
+  copyright = {arXiv.org perpetual, non-exclusive license}
+}
+```