Update README.md
Browse files
README.md
CHANGED
@@ -251,7 +251,7 @@ For more details please refer to our [paper](https://arxiv.org/abs/2402.10422) a
|
|
251 |
|
252 |
This version of ZeroSwot is trained with ASR data from CommonVoice, and adapting [wav2vec2.0-large](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self) to the [nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) model.
|
253 |
|
254 |
-
<div align=center><img src="methodology.png" height="100%" width="100%"/></div>
|
255 |
|
256 |
## Usage
|
257 |
|
@@ -284,7 +284,7 @@ nllb_model.eval()
|
|
284 |
nllb_model.to("cuda")
|
285 |
|
286 |
# Load sample .wav
|
287 |
-
audio = load_and_resample_audio("sample.wav")
|
288 |
input_values = processor(audio, sampling_rate=16000, return_tensors="pt").cuda()
|
289 |
|
290 |
# translation to German
|
|
|
251 |
|
252 |
This version of ZeroSwot is trained with ASR data from CommonVoice, and adapting [wav2vec2.0-large](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self) to the [nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) model.
|
253 |
|
254 |
+
<div align=center><img src="resources/methodology.png" height="100%" width="100%"/></div>
|
255 |
|
256 |
## Usage
|
257 |
|
|
|
284 |
nllb_model.to("cuda")
|
285 |
|
286 |
# Load sample .wav
|
287 |
+
audio = load_and_resample_audio("resources/sample.wav")
|
288 |
input_values = processor(audio, sampling_rate=16000, return_tensors="pt").cuda()
|
289 |
|
290 |
# translation to German
|