license: mit
datasets:
- mozilla-foundation/common_voice_16_1
language:
- es
library_name: transformers
pipeline_tag: automatic-speech-recognition
tags:
- spanish
- speech
- recognition
- whisper
- distl-whisper
distil-whisper-large-v3-es
This is the repository for a distilled version of the Whisper v3 large model trained on the Mozilla Common Voice dataset v16.1.
Usage
Distil-Whisper is supported in Hugging Face 🤗 Transformers from version 4.35 onwards. To run the model, first install the latest version of the Transformers library. For this example, we'll also install 🤗 Datasets to load toy audio dataset from the Hugging Face Hub:
pip install --upgrade pip
pip install --upgrade transformers accelerate datasets[audio]
Short-Form Transcription
The model can be used with the pipeline
class to transcribe short-form audio files (< 30-seconds) as follows:
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
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 = "distil-whisper/distil-large-v2"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
max_new_tokens=128,
torch_dtype=torch_dtype,
device=device,
)
dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
sample = dataset[0]["audio"]
result = pipe(sample)
print(result["text"])
To transcribe a local audio file, simply pass the path to your audio file when you call the pipeline:
- result = pipe(sample)
+ result = pipe("audio.mp3")
Long-Form Transcription
Distil-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).
To enable chunking, pass the chunk_length_s parameter to the pipeline. For Distil-Whisper, a chunk length of 15-seconds
is optimal. To activate batching, pass the argument batch_size:
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
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 = "marianbasti/distil-whisper-large-v3-es"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
max_new_tokens=128,
chunk_length_s=15,
batch_size=16,
torch_dtype=torch_dtype,
device=device,
)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]
result = pipe(sample)
print(result["text"])
Speculative Decoding
Distil-Whisper 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.
In the following code-snippet, we load the assistant Distil-Whisper model standalone to the main Whisper pipeline. We then specify it as the "assistant model" for generation:
from transformers import pipeline, AutoModelForCausalLM, AutoModelForSpeechSeq2Seq, AutoProcessor
import torch
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 = "marianbasti/distil-whisper-large-v3-es"
assistant_model = AutoModelForCausalLM.from_pretrained(
assistant_model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
assistant_model.to(device)
model_id = "openai/whisper-large-v2"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
max_new_tokens=128,
generate_kwargs={"assistant_model": assistant_model},
torch_dtype=torch_dtype,
device=device,
)
dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
sample = dataset[0]["audio"]
result = pipe(sample)
print(result["text"])
Training
The model was trained for 40,000 optimisation steps (or four epochs), and the following training parameters:
--teacher_model_name_or_path "openai/whisper-large-v3"
--train_dataset_name "mozilla-foundation/common_voice_16_1"
--train_dataset_config_name "es"
--train_split_name "train"
--text_column_name "sentence"
--eval_dataset_name "mozilla-foundation/common_voice_16_1"
--eval_dataset_config_name "es"
--eval_split_name "validation"
--eval_text_column_name "sentence"
--eval_steps 5000
--save_steps 5000
--warmup_steps 500
--learning_rate 1e-4
--lr_scheduler_type "linear"
--logging_steps 25
--save_total_limit 1
--max_steps 40000
Results
The distilled model performs with a 5.874% normalized WER. Further training would yield better results
License
Distil-Whisper inherits the MIT license from OpenAI's Whisper model.
Citation
If you use this model, please consider citing the Distil-Whisper paper:
@misc{gandhi2023distilwhisper,
title={Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling},
author={Sanchit Gandhi and Patrick von Platen and Alexander M. Rush},
year={2023},
eprint={2311.00430},
archivePrefix={arXiv},
primaryClass={cs.CL}
}