Downloads · 30 days
18
3% of all-time downloads
bofenghuang/wav2vec2-xls-r-1b-cv9-fr
wav2vec2-xls-r-1b-cv9-fr is a automatic speech recognition model from bofenghuang. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMONVOICE90 - FR dataset.
Downloads · 30 days
18
3% of all-time downloads
All-time downloads
526
Public
Repo size
7.9 GB
Likes
1
Public
Click a slice to open those files.
.bin4.1 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMON_VOICE_9_0 - FR dataset.
import torch
import torchaudio
from transformers import AutoModelForCTC, Wav2Vec2Processor
processor = Wav2Vec2Processor.from_pretrained("bhuang/wav2vec2-xls-r-1b-cv9-fr")
model = AutoModelForCTC.from_pretrained("bhuang/wav2vec2-xls-r-1b-cv9-fr").cuda()
# path to your audio file
wav_path = "example.wav"
waveform, sample_rate = torchaudio.load(wav_path)
waveform = waveform.squeeze(axis=0) # mono
# resample
if sample_rate != 16_000:
resampler = torchaudio.transforms.Resample(sample_rate, 16_000)
waveform = resampler(waveform)
# normalize
input_dict = processor(waveform, sampling_rate=16_000, return_tensors="pt")
with torch.inference_mode():
logits = model(input_dict.input_values.to("cuda")).logits
# decode
predicted_ids = torch.argmax(logits, dim=-1)
predicted_sentence = processor.batch_decode(predicted_ids)[0]
import torch
import torchaudio
from transformers import AutoModelForCTC, Wav2Vec2ProcessorWithLM
processor_with_lm = Wav2Vec2ProcessorWithLM.from_pretrained("bhuang/wav2vec2-xls-r-1b-cv9-fr")
model = AutoModelForCTC.from_pretrained("bhuang/wav2vec2-xls-r-1b-cv9-fr").cuda()
model_sampling_rate = processor_with_lm.feature_extractor.sampling_rate
# path to your audio file
wav_path = "example.wav"
waveform, sample_rate = torchaudio.load(wav_path)
waveform = waveform.squeeze(axis=0) # mono
# resample
if sample_rate != 16_000:
resampler = torchaudio.transforms.Resample(sample_rate, 16_000)
waveform = resampler(waveform)
# normalize
input_dict = processor_with_lm(waveform, sampling_rate=16_000, return_tensors="pt")
with torch.inference_mode():
logits = model(input_dict.input_values.to("cuda")).logits
predicted_sentence = processor_with_lm.batch_decode(logits.cpu().numpy()).text[0]
mozilla-foundation/common_voice_9_0python eval.py \
--model_id "bhuang/wav2vec2-xls-r-1b-cv9-fr" \
--dataset "mozilla-foundation/common_voice_9_0" \
--config "fr" \
--split "test" \
--log_outputs \
--outdir "outputs/results_mozilla-foundatio_common_voice_9_0_with_lm"
speech-recognition-community-v2/dev_datapython eval.py \
--model_id "bhuang/wav2vec2-xls-r-1b-cv9-fr" \
--dataset "speech-recognition-community-v2/dev_data" \
--config "fr" \
--split "validation" \
--chunk_length_s 5.0 \
--stride_length_s 1.0 \
--log_outputs \
--outdir "outputs/results_speech-recognition-community-v2_dev_data_with_lm"