Update README.md
Browse files
README.md
CHANGED
@@ -54,7 +54,7 @@ The compression module is a light-weight transformer that takes as input the hid
|
|
54 |
|
55 |
## Version
|
56 |
|
57 |
-
This version of ZeroSwot is trained with ASR data from CommonVoice
|
58 |
|
59 |
We have more versions available:
|
60 |
|
@@ -91,7 +91,7 @@ def load_and_resample_audio(audio_path, target_sr=16000):
|
|
91 |
|
92 |
# Load processors and tokenizers
|
93 |
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
|
94 |
-
tokenizer = NllbTokenizer.from_pretrained("johntsi/nllb-200-distilled-
|
95 |
|
96 |
# Load ZeroSwot Encoder
|
97 |
commit_hash = "762878c55bf91406318983c724db22590a828e96"
|
@@ -102,7 +102,7 @@ zeroswot_encoder.eval()
|
|
102 |
zeroswot_encoder.to("cuda")
|
103 |
|
104 |
# Load NLLB Model
|
105 |
-
nllb_model = AutoModelForSeq2SeqLM.from_pretrained("johntsi/nllb-200-distilled-
|
106 |
nllb_model.eval()
|
107 |
nllb_model.to("cuda")
|
108 |
|
|
|
54 |
|
55 |
## Version
|
56 |
|
57 |
+
This version of ZeroSwot is trained with ASR data from CommonVoice. It adapts [wav2vec2.0-large](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self) to the embedding space of the [nllb-200-distilled-1.3B_covost2](https://huggingface.co/johntsi/nllb-200-distilled-600M_covost2_en-to-15) model, which is a multilingually finetuned NLLB on MuST-C MT data.
|
58 |
|
59 |
We have more versions available:
|
60 |
|
|
|
91 |
|
92 |
# Load processors and tokenizers
|
93 |
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
|
94 |
+
tokenizer = NllbTokenizer.from_pretrained("johntsi/nllb-200-distilled-1.3B_covost2_en-to-15")
|
95 |
|
96 |
# Load ZeroSwot Encoder
|
97 |
commit_hash = "762878c55bf91406318983c724db22590a828e96"
|
|
|
102 |
zeroswot_encoder.to("cuda")
|
103 |
|
104 |
# Load NLLB Model
|
105 |
+
nllb_model = AutoModelForSeq2SeqLM.from_pretrained("johntsi/nllb-200-distilled-1.3B_covost2_en-to-15")
|
106 |
nllb_model.eval()
|
107 |
nllb_model.to("cuda")
|
108 |
|