Update README.md

README.md

@@ -24,90 +24,104 @@ This is the "medium" variant of the unified model, which enables multiple tasks
 - Text-to-text translation (T2TT)
 - Automatic speech recognition (ASR)
 
-You can perform all the above tasks from one single model - `SeamlessM4TModel`, but each task also has its own dedicated sub-model.
+You can perform all the above tasks from one single model, [`SeamlessM4TModel`](https://moon-ci-docs.huggingface.co/docs/transformers/pr_25693/en/model_doc/seamless_m4t#transformers.SeamlessM4TModel), but each task also has its own dedicated sub-model.
 
 
-## Usage
+## 🤗 Usage
 
 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-medium")
->>> model = SeamlessM4TModel.from_pretrained("ylacombe/hf-seamless-m4t-medium")
+processor = AutoProcessor.from_pretrained("ylacombe/hf-seamless-m4t-medium")
+model = SeamlessM4TModel.from_pretrained("ylacombe/hf-seamless-m4t-medium")
 ```
 
 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`]. Here is an example showing how to generate speech from English to Russian.
+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.
 
 ```python
->>> inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
+inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
 
->>> audio_array = model.generate(**inputs, tgt_lang="rus")
->>> audio_array = audio_array[0].cpu().numpy().squeeze()
+audio_array = model.generate(**inputs, tgt_lang="rus")
+audio_array = audio_array[0].cpu().numpy().squeeze()
 ```
 
 You can also translate directly from a speech waveform. Here is an example from Arabic to English:
 
 ```python
->>> from datasets import load_dataset
+from datasets import load_dataset
 
->>> dataset = load_dataset("arabic_speech_corpus", split="test[0:1]")
+dataset = load_dataset("arabic_speech_corpus", split="test[0:1]")
+audio_sample = dataset["audio"][0]["array"]
+inputs = processor(audios = audio_sample, return_tensors="pt")
 
->>> audio_sample = dataset["audio"][0]["array"]
- 
->>> inputs = processor(audios = audio_sample, return_tensors="pt")
+audio_array = model.generate(**inputs, tgt_lang="rus")
+audio_array = audio_array[0].cpu().numpy().squeeze()
+```
+
+Listen to the speech samples either in an ipynb notebook:
+
+```python
+from IPython.display import Audio
 
->>> audio_array = model.generate(**inputs, tgt_lang="rus")
->>> audio_array = audio_array[0].cpu().numpy().squeeze()
+sampling_rate = model.config.sample_rate
+Audio(audio_array, rate=sampling_rate)
+```
+
+Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
+
+```python
+import scipy
+
+sampling_rate = model.config.sample_rate
+scipy.io.wavfile.write("seamless_m4t_out.wav", rate=sampling_rate, data=audio_array)
 ```
 
 #### Tips
 
-[`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.
+[`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-medium")
+from transformers import SeamlessM4TForSpeechToSpeech
+model = SeamlessM4TForSpeechToSpeech.from_pretrained("ylacombe/hf-seamless-m4t-medium")
 ```
 
 
 ### Text
 
-Similarly, you can generate translated text from text or audio files, this time using the dedicated models.
+Similarly, you can generate translated text from text or audio files. This time, let's use the dedicated models as example.
 
 ```python
->>> from transformers import SeamlessM4TForSpeechToText
->>> model = SeamlessM4TForSpeechToText.from_pretrained("ylacombe/hf-seamless-m4t-medium")
->>> 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 SeamlessM4TForSpeechToText
+model = SeamlessM4TForSpeechToText.from_pretrained("ylacombe/hf-seamless-m4t-medium")
+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)
 ```
 
 And from text:
 
 ```python
->>> from transformers import SeamlessM4TForTextToText
->>> model = SeamlessM4TForTextToText.from_pretrained("ylacombe/hf-seamless-m4t-medium")
->>> inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
+from transformers import SeamlessM4TForTextToText
+model = SeamlessM4TForTextToText.from_pretrained("ylacombe/hf-seamless-m4t-medium")
+inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
 
->>> output_tokens = model.generate(**inputs, tgt_lang="fra")
->>> translated_text = processor.decode(output_tokens.tolist()[0], skip_special_tokens=True)
+output_tokens = model.generate(**inputs, tgt_lang="fra")
+translated_text = processor.decode(output_tokens.tolist()[0], skip_special_tokens=True)
 ```
 
 #### Tips
 
 Three last tips:
 
-1. [`SeamlessM4TModel`] can generate text and/or speech. Pass `generate_speech=False` to [`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.
+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.
-