Update README.md

README.md

@@ -50,15 +50,86 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+The architecture is the same as [openai/whisper-medium](https://huggingface.co/openai/whisper-medium).
 
-## Intended uses & limitations
+## Training and evaluation data
 
-More information needed
+The model was trained on the Common Voice 11.0 dataset (`train+validation+other splits`) and the Romanian speech synthesis corpus, and was tested on the `test` split of the Common Voice 11.0 dataset.
 
-## Training and evaluation data
+## Usage
+Inference with 🤗 Pipeline
+```python
+import torch
+from datasets import load_dataset
+from transformers import pipeline
+
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+# Load pipeline
+pipe = pipeline("automatic-speech-recognition", model="gigant/whisper-medium-romanian", device=device)
+# NB: set forced_decoder_ids for generation utils
+pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="ro", task="transcribe")
+
+# Load data
+ds_mcv_test = load_dataset("mozilla-foundation/common_voice_11_0", "ro", split="test", streaming=True)
+test_segment = next(iter(ds_mcv_test))
+waveform = test_segment["audio"]
+
+# NB: decoding option
+# limit the maximum number of generated tokens to 225
+pipe.model.config.max_length = 225 + 1
+# sampling
+# pipe.model.config.do_sample = True
+# beam search
+# pipe.model.config.num_beams = 5
+# return
+# pipe.model.config.return_dict_in_generate = True
+# pipe.model.config.output_scores = True
+# pipe.model.config.num_return_sequences = 5
+# Run
+generated_sentences = pipe(waveform)["text"]
+```
+Inference with 🤗 low-level APIs
+```python
+import torch
+import torchaudio
+
+from datasets import load_dataset
+from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+# Load model
+model = AutoModelForSpeechSeq2Seq.from_pretrained("gigant/whisper-medium-romanian").to(device)
+processor = AutoProcessor.from_pretrained("gigant/whisper-medium-romanian", language="romanian", task="transcribe")
+
+# NB: set forced_decoder_ids for generation utils
+model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="ro", task="transcribe")
+# 16_000
+model_sample_rate = processor.feature_extractor.sampling_rate
+
+# Load data
+ds_mcv_test = load_dataset("mozilla-foundation/common_voice_11_0", "ro", split="test", streaming=True)
+test_segment = next(iter(ds_mcv_test))
+waveform = torch.from_numpy(test_segment["audio"]["array"])
+sample_rate = test_segment["audio"]["sampling_rate"]
+# Resample
+if sample_rate != model_sample_rate:
+    resampler = torchaudio.transforms.Resample(sample_rate, model_sample_rate)
+    waveform = resampler(waveform)
+# Get feat
+inputs = processor(waveform, sampling_rate=model_sample_rate, return_tensors="pt")
+input_features = inputs.input_features
+input_features = input_features.to(device)
+
+# Generate
+generated_ids = model.generate(inputs=input_features, max_new_tokens=225)  # greedy
+# generated_ids = model.generate(inputs=input_features, max_new_tokens=225, num_beams=5)  # beam search
+# Detokenize
+generated_sentences = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+# Normalise predicted sentences if necessary
+```
 
-More information needed
+The code was adapted from [bofenghuang/deprecated-whisper-large-v2-cv11-french-punct-plus](https://huggingface.co/bofenghuang/deprecated-whisper-large-v2-cv11-french-punct-plus).
 
 ## Training procedure