Update README.md

README.md

@@ -34,97 +34,86 @@ You can perform all the above tasks from one single model, [`SeamlessM4TModel`](
 First, load the processor and a checkpoint of the model:
 
 ```python
-from transformers import AutoProcessor, SeamlessM4TModel
+>>> from transformers import AutoProcessor, SeamlessM4TModel
 
-processor = AutoProcessor.from_pretrained("ylacombe/hf-seamless-m4t-large")
-model = SeamlessM4TModel.from_pretrained("ylacombe/hf-seamless-m4t-large")
+>>> processor = AutoProcessor.from_pretrained("facebook/hf-seamless-m4t-large")
+>>> model = SeamlessM4TModel.from_pretrained("facebook/hf-seamless-m4t-large")
 ```
 
 You can seamlessly use this model on text or on audio, to generated either translated text or translated audio.
 
-### Speech
-
-You can easily generate translated speech with [`SeamlessM4TModel.generate`](https://moon-ci-docs.huggingface.co/docs/transformers/pr_25693/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel.generate). Here is an example showing how to generate speech from English to Russian.
+Here is how to use the processor to process text and audio:
 
 ```python
-inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
+>>> # let's load an audio sample from an Arabic speech corpus
+>>> from datasets import load_dataset
+>>> dataset = load_dataset("arabic_speech_corpus", split="test", streaming=True)
+>>> audio_sample = next(iter(dataset))["audio"]
+
+>>> # now, process it
+>>> audio_inputs = processor(audios=audio_sample["array"], return_tensors="pt")
 
-audio_array = model.generate(**inputs, tgt_lang="rus")
-audio_array = audio_array[0].cpu().numpy().squeeze()
+>>> # now, process some English test as well
+>>> text_inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
 ```
 
-You can also translate directly from a speech waveform. Here is an example from Arabic to English:
 
-```python
-from datasets import load_dataset
+### Speech
 
-dataset = load_dataset("arabic_speech_corpus", split="test[0:1]")
-audio_sample = dataset["audio"][0]["array"]
-inputs = processor(audios = audio_sample, return_tensors="pt")
+[`SeamlessM4TModel`] can *seamlessly* generate text or speech with few or no changes. Let's target Russian voice translation:
 
-audio_array = model.generate(**inputs, tgt_lang="rus")
-audio_array = audio_array[0].cpu().numpy().squeeze()
+```python
+>>> audio_array_from_text = model.generate(**text_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()
+>>> audio_array_from_audio = model.generate(**audio_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()
 ```
 
-Listen to the speech samples either in an ipynb notebook:
+With basically the same code, I've translated English text and Arabic speech to Russian speech samples.
 
-```python
-from IPython.display import Audio
+### Text
 
-sampling_rate = model.config.sample_rate
-Audio(audio_array, rate=sampling_rate)
-```
+Similarly, you can generate translated text from audio files or from text with the same model. You only have to pass `generate_speech=False` to [`SeamlessM4TModel.generate`].
+This time, let's translate to French.
 
-Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
+```python 
+>>> # from audio
+>>> output_tokens = model.generate(**audio_inputs, tgt_lang="fra", generate_speech=False)
+>>> translated_text_from_audio = processor.decode(output_tokens[0].tolist()[0], skip_special_tokens=True)
 
-```python
-import scipy
-
-sampling_rate = model.config.sample_rate
-scipy.io.wavfile.write("seamless_m4t_out.wav", rate=sampling_rate, data=audio_array)
+>>> # from text
+>>> output_tokens = model.generate(**text_inputs, tgt_lang="fra", generate_speech=False)
+>>> translated_text_from_text = processor.decode(output_tokens[0].tolist()[0], skip_special_tokens=True)
 ```
 
-#### Tips
+### Tips
 
-[`SeamlessM4TModel`](https://moon-ci-docs.huggingface.co/docs/transformers/pr_25693/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel) is transformers top level model to generate speech and text, but you can also use dedicated models that perform the task without additional components, thus reducing the memory footprint.
-For example, you can replace the previous snippet with the model dedicated to the S2ST task:
 
-```python
-from transformers import SeamlessM4TForSpeechToSpeech
-model = SeamlessM4TForSpeechToSpeech.from_pretrained("ylacombe/hf-seamless-m4t-large")
-```
+#### 1. Use dedicated models
 
+[`SeamlessM4TModel`] is transformers top level model to generate speech and text, but you can also use dedicated models that perform the task without additional components, thus reducing the memory footprint.
+For example, you can replace the audio-to-audio generation snippet with the model dedicated to the S2ST task, the rest is exactly the same code: 
 
-### Text
+```python
+>>> from transformers import SeamlessM4TForSpeechToSpeech
+>>> model = SeamlessM4TForSpeechToSpeech.from_pretrained("facebook/hf-seamless-m4t-large")
+```
 
-Similarly, you can generate translated text from text or audio files. This time, let's use the dedicated models as example.
+Or you can replace the text-to-text generation snippet with the model dedicated to the T2TT task, you only have to remove `generate_speech=False`.
 
 ```python
-from transformers import SeamlessM4TForSpeechToText
-model = SeamlessM4TForSpeechToText.from_pretrained("ylacombe/hf-seamless-m4t-large")
-audio_sample = dataset["audio"][0]["array"]
-inputs = processor(audios = audio_sample, return_tensors="pt")
-
-output_tokens = model.generate(**inputs, tgt_lang="fra")
-translated_text = processor.decode(output_tokens.tolist()[0], skip_special_tokens=True)
+>>> from transformers import SeamlessM4TForTextToText
+>>> model = SeamlessM4TForTextToText.from_pretrained("facebook/hf-seamless-m4t-large")
 ```
 
-And from text:
+Feel free to try out [`SeamlessM4TForSpeechToText`] and [`SeamlessM4TForTextToSpeech`] as well.
 
-```python
-from transformers import SeamlessM4TForTextToText
-model = SeamlessM4TForTextToText.from_pretrained("ylacombe/hf-seamless-m4t-large")
-inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
+#### 2. Change the speaker identity
 
-output_tokens = model.generate(**inputs, tgt_lang="fra")
-translated_text = processor.decode(output_tokens.tolist()[0], skip_special_tokens=True)
-```
+You have the possibility to change the speaker used for speech synthesis with the `spkr_id` argument. Some `spkr_id` works better than other for some languages!
 
-#### Tips
+#### 3. Change the speaker identity
 
-Three last tips:
+You can use different [generation strategies](./generation_strategies) for speech and text generation, e.g `.generate(input_ids=input_ids, text_num_beams=4, speech_do_sample=True)` which will successively perform beam-search decoding on the text model, and multinomial sampling on the speech model.
 
-1. [`SeamlessM4TModel`](https://moon-ci-docs.huggingface.co/docs/transformers/pr_25693/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel) can generate text and/or speech. Pass `generate_speech=False` to [`SeamlessM4TModel.generate`](https://moon-ci-docs.huggingface.co/docs/transformers/pr_25693/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel.generate) to only generate text. You also have the possibility to pass `return_intermediate_token_ids=True`, to get both text token ids and the generated speech.
-2. You have the possibility to change the speaker used for speech synthesis with the `spkr_id` argument.
-3. You can use different [generation strategies](./generation_strategies) for speech and text generation, e.g `.generate(input_ids=input_ids, text_num_beams=4, speech_do_sample=True)` which will successively perform beam-search decoding on the text model, and multinomial sampling on the speech model.
+#### 4. Generate speech and text at the same time
 
+Use `return_intermediate_token_ids=True` with [`SeamlessM4TModel`] to return both speech and text !